id stringlengths 11 11 | task stringclasses 18
values | messages stringlengths 1.78k 4.74k | domains stringlengths 48 170 | difficulty stringclasses 4
values | outcome stringclasses 5
values | available_tools stringlengths 42 128 | constraints stringlengths 119 266 | expected_outputs stringclasses 18
values | execution_plan stringclasses 18
values | tool_trace stringlengths 2 1.55k | error stringclasses 9
values | clarification stringclasses 8
values | verification stringclasses 18
values | final_result stringlengths 177 462 | scenario_family stringclasses 18
values | split stringclasses 3
values | synthetic bool 1
class | generator_version stringclasses 1
value |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
atm_0002001 | Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. Context: Seve... | ["document_creation","data_analysis","decision_making","financial_analysis","workflow_automation","research"] | intermediate | success | ["email_client","database","testing_framework","spreadsheet","api_client","file_manager","browser"] | ["Preserve original source data.","Use accessible and understandable interfaces.","Report errors instead of silently ignoring them.","Validate calculations before presenting conclusions.","Respect dependencies between tasks."] | ["assumptions","calculations","scenario_comparison","decision_report"] | [{"step":1,"action":"Prepare assumptions","purpose":"Produce and validate assumptions","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare scenario comparison","purpose":"Produce and validate scenario comparison","depends... | [{"step":1,"action":"Prepare assumptions","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"a... | [{"item":"assumptions","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"scenario_comparison","check":"Check structure, completeness and consistency.","result":"simulat... | {"status":"success","completed_outputs":["assumptions","calculations","scenario_comparison","decision_report"],"message":"The planned outputs are represented as completed in this synthetic example."} | financial_decision | train | true | 1.0.0 | ||
atm_0002002 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The available informa... | ["api_integration","backend_engineering","software_testing","app_development"] | expert | failed | ["python","email_client","testing_framework","document_editor","api_client"] | ["Do not claim that an action succeeded without evidence.","Explain uncertainty and missing information.","Avoid exposing credentials or private information.","Validate calculations before presenting conclusions.","Report errors instead of silently ignoring them."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3... | {"code":"invalid_format","description":"An input file has an unexpected format."} | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | api_product | train | true | 1.0.0 | |
atm_0002003 | Coordinate a project with deadlines, dependencies, stakeholders and documented decisions. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Coordinate a project with deadlines, dependencies, stakeholders and documented decisions. Context: The task re... | ["project_management","document_creation","email_writing","decision_making","app_development","cross_domain_execution","debugging"] | intermediate | clarification | ["api_client","code_editor","email_client","chart_generator","testing_framework"] | ["Do not claim that an action succeeded without evidence.","Respect dependencies between tasks.","Keep outputs structured and easy to inspect.","Preserve original source data.","Explain uncertainty and missing information."] | ["project_plan","timeline","decision_log","communications"] | [{"step":1,"action":"Prepare project plan","purpose":"Produce and validate project plan","depends_on":[]},{"step":2,"action":"Prepare timeline","purpose":"Produce and validate timeline","depends_on":[1]},{"step":3,"action":"Prepare decision log","purpose":"Produce and validate decision log","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare project plan","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare timeline","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Which currency and reporting period should be used? | [{"item":"project_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"timeline","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"decision_log","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"needs_clarification","completed_outputs":[],"question":"Which currency and reporting period should be used?","message":"Pause consequential execution until the ambiguity is resolved."} | project_coordination | train | true | 1.0.0 | |
atm_0002004 | Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. Context: The avail... | ["terminal_operations","debugging","project_management","software_testing","database_management","research","workflow_automation"] | expert | recovered | ["python","browser","spreadsheet","document_editor","testing_framework","email_client"] | ["Preserve original source data.","Avoid exposing credentials or private information.","Use accessible and understandable interfaces."] | ["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"] | [{"step":1,"action":"Prepare incident summary","purpose":"Produce and validate incident summary","depends_on":[]},{"step":2,"action":"Prepare root cause hypothesis","purpose":"Produce and validate root cause hypothesis","depends_on":[1]},{"step":3,"action":"Prepare recovery plan","purpose":"Produce and validate recover... | [{"step":1,"action":"Prepare incident summary","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare root cause hypothesis","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":... | {"code":"dependency_error","description":"A required dependency is unavailable."} | [{"item":"incident_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"root_cause_hypothesis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"recovery_plan","check":"Check structure, completeness and consistency.","result":... | {"status":"recovered","completed_outputs":["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Request the missing input from the user.","Inspect the failing component and isolate the cause... | test_recovery_workflow | test | true | 1.0.0 | |
atm_0002005 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The user ex... | ["decision_making","research","document_creation","email_writing","backend_engineering","software_testing"] | intermediate | success | ["chart_generator","spreadsheet","testing_framework","email_client"] | ["Report errors instead of silently ignoring them.","Do not claim that an action succeeded without evidence.","Avoid exposing credentials or private information.","Respect dependencies between tasks."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"acti... | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"success","completed_outputs":["research_summary","comparison","proposal","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | research_to_proposal | train | true | 1.0.0 | ||
atm_0002006 | Coordinate a complex application delivery with technical dependencies and stakeholder communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Coordinate a complex application delivery with technical dependencies and stakeholder communication. Context: ... | ["email_writing","backend_engineering","project_management","app_development","data_analysis","terminal_operations","software_testing"] | very_complex | success | ["email_client","testing_framework","spreadsheet","python","browser","terminal","database","chart_generator"] | ["Validate calculations before presenting conclusions.","Keep outputs structured and easy to inspect.","Report errors instead of silently ignoring them.","Avoid exposing credentials or private information.","Use accessible and understandable interfaces."] | ["delivery_plan","technical_design","dependency_report","email_draft"] | [{"step":1,"action":"Prepare delivery plan","purpose":"Produce and validate delivery plan","depends_on":[]},{"step":2,"action":"Prepare technical design","purpose":"Produce and validate technical design","depends_on":[1]},{"step":3,"action":"Prepare dependency report","purpose":"Produce and validate dependency report",... | [{"step":1,"action":"Prepare delivery plan","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare technical design","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepar... | [{"item":"delivery_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"technical_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_report","check":"Check structure, completeness and consistency.","result":"sim... | {"status":"success","completed_outputs":["delivery_plan","technical_design","dependency_report","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | test_complex_delivery | test | true | 1.0.0 | ||
atm_0002007 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The workflow should a... | ["software_testing","api_integration","app_development","backend_engineering"] | advanced | success | ["document_editor","terminal","spreadsheet","file_manager","chart_generator","api_client","code_editor","browser"] | ["Keep outputs structured and easy to inspect.","Preserve original source data.","Do not claim that an action succeeded without evidence.","Avoid exposing credentials or private information.","Respect dependencies between tasks."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare... | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"success","completed_outputs":["api_contract","backend_design","interface_spec","test_plan"],"message":"The planned outputs are represented as completed in this synthetic example."} | api_product | train | true | 1.0.0 | ||
atm_0002008 | Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. Context: The user ... | ["project_management","software_testing","terminal_operations","debugging","cross_domain_execution"] | very_complex | impossible | ["python","terminal","email_client","chart_generator","spreadsheet"] | ["Do not claim that an action succeeded without evidence.","Keep outputs structured and easy to inspect.","Respect dependencies between tasks.","Report errors instead of silently ignoring them.","Use accessible and understandable interfaces."] | ["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"] | [{"step":1,"action":"Prepare incident summary","purpose":"Produce and validate incident summary","depends_on":[]},{"step":2,"action":"Prepare root cause hypothesis","purpose":"Produce and validate root cause hypothesis","depends_on":[1]},{"step":3,"action":"Prepare recovery plan","purpose":"Produce and validate recover... | [{"step":1,"action":"Prepare incident summary","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare root cause hypothesis","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | [{"item":"incident_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"root_cause_hypothesis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"recovery_plan","check":"Check structure, completeness and consistency.","result":... | {"status":"impossible","completed_outputs":[],"reason":"The requested outputs contradict a stated constraint.","message":"Explain the limitation and identify a feasible alternative."} | test_recovery_workflow | test | true | 1.0.0 | ||
atm_0002009 | Coordinate a project with deadlines, dependencies, stakeholders and documented decisions. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Coordinate a project with deadlines, dependencies, stakeholders and documented decisions. Context: Some assump... | ["document_creation","decision_making","project_management","email_writing","cross_domain_execution","ui_ux_design"] | expert | success | ["code_editor","python","spreadsheet","document_editor","database","testing_framework","browser"] | ["Preserve original source data.","Respect dependencies between tasks.","Validate calculations before presenting conclusions."] | ["project_plan","timeline","decision_log","communications"] | [{"step":1,"action":"Prepare project plan","purpose":"Produce and validate project plan","depends_on":[]},{"step":2,"action":"Prepare timeline","purpose":"Produce and validate timeline","depends_on":[1]},{"step":3,"action":"Prepare decision log","purpose":"Produce and validate decision log","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare project plan","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare timeline","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"P... | [{"item":"project_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"timeline","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"decision_log","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"success","completed_outputs":["project_plan","timeline","decision_log","communications"],"message":"The planned outputs are represented as completed in this synthetic example."} | project_coordination | train | true | 1.0.0 | ||
atm_0002010 | Design and implement a user-friendly application with a backend, database and verification plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design and implement a user-friendly application with a backend, database and verification plan. Context: The ... | ["software_testing","database_management","app_development","backend_engineering","document_creation"] | expert | failed | ["document_editor","chart_generator","spreadsheet","database","python","testing_framework","terminal"] | ["Do not claim that an action succeeded without evidence.","Report errors instead of silently ignoring them.","Preserve original source data."] | ["application_design","backend_plan","database_schema","test_report"] | [{"step":1,"action":"Prepare application design","purpose":"Produce and validate application design","depends_on":[]},{"step":2,"action":"Prepare backend plan","purpose":"Produce and validate backend plan","depends_on":[1]},{"step":3,"action":"Prepare database schema","purpose":"Produce and validate database schema","d... | [{"step":1,"action":"Prepare application design","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend plan","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare... | {"code":"unavailable_service","description":"An external service cannot be confirmed as available."} | [{"item":"application_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"database_schema","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | fullstack_delivery | train | true | 1.0.0 | |
atm_0002011 | Interpret unfamiliar structured data, document limitations and prepare a reasoned recommendation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Interpret unfamiliar structured data, document limitations and prepare a reasoned recommendation. Context: The... | ["data_analysis","document_creation","financial_analysis","decision_making","ui_ux_design","database_management"] | advanced | success | ["code_editor","browser","email_client","chart_generator"] | ["Explain uncertainty and missing information.","Validate calculations before presenting conclusions.","Do not claim that an action succeeded without evidence.","Respect dependencies between tasks."] | ["data_assessment","calculations","limitations","recommendation"] | [{"step":1,"action":"Prepare data assessment","purpose":"Produce and validate data assessment","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare limitations","purpose":"Produce and validate limitations","depends_on":[2]... | [{"step":1,"action":"Prepare data assessment","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"... | [{"item":"data_assessment","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"limitations","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"success","completed_outputs":["data_assessment","calculations","limitations","recommendation"],"message":"The planned outputs are represented as completed in this synthetic example."} | test_data_decision | test | true | 1.0.0 | ||
atm_0002012 | Plan a small software product from requirements through implementation, testing and documentation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a small software product from requirements through implementation, testing and documentation. Context: Th... | ["backend_engineering","document_creation","software_testing","project_management","app_development","api_integration","data_analysis"] | expert | failed | ["python","api_client","testing_framework","code_editor","database","browser"] | ["Use accessible and understandable interfaces.","Preserve original source data.","Keep outputs structured and easy to inspect.","Explain uncertainty and missing information.","Respect dependencies between tasks."] | ["requirements","architecture","implementation_plan","test_report","documentation"] | [{"step":1,"action":"Prepare requirements","purpose":"Produce and validate requirements","depends_on":[]},{"step":2,"action":"Prepare architecture","purpose":"Produce and validate architecture","depends_on":[1]},{"step":3,"action":"Prepare implementation plan","purpose":"Produce and validate implementation plan","depen... | [{"step":1,"action":"Prepare requirements","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare architecture","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prep... | {"code":"dependency_error","description":"A required dependency is unavailable."} | [{"item":"requirements","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"architecture","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"implementation_plan","check":"Check structure, completeness and consistency.","result":"simula... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | integrated_product | train | true | 1.0.0 | |
atm_0002013 | Coordinate a project with deadlines, dependencies, stakeholders and documented decisions. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Coordinate a project with deadlines, dependencies, stakeholders and documented decisions. Context: The outputs... | ["decision_making","document_creation","email_writing","project_management"] | intermediate | success | ["api_client","testing_framework","spreadsheet","terminal","database"] | ["Use accessible and understandable interfaces.","Do not claim that an action succeeded without evidence.","Respect dependencies between tasks.","Avoid exposing credentials or private information.","Explain uncertainty and missing information."] | ["project_plan","timeline","decision_log","communications"] | [{"step":1,"action":"Prepare project plan","purpose":"Produce and validate project plan","depends_on":[]},{"step":2,"action":"Prepare timeline","purpose":"Produce and validate timeline","depends_on":[1]},{"step":3,"action":"Prepare decision log","purpose":"Produce and validate decision log","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare project plan","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare timeline","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare... | [{"item":"project_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"timeline","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"decision_log","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"success","completed_outputs":["project_plan","timeline","decision_log","communications"],"message":"The planned outputs are represented as completed in this synthetic example."} | project_coordination | train | true | 1.0.0 | ||
atm_0002014 | Interpret unfamiliar structured data, document limitations and prepare a reasoned recommendation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Interpret unfamiliar structured data, document limitations and prepare a reasoned recommendation. Context: The... | ["document_creation","decision_making","financial_analysis","data_analysis","cross_domain_execution","ui_ux_design","project_management"] | very_complex | failed | ["api_client","spreadsheet","database","terminal","chart_generator","file_manager"] | ["Validate calculations before presenting conclusions.","Use accessible and understandable interfaces.","Explain uncertainty and missing information."] | ["data_assessment","calculations","limitations","recommendation"] | [{"step":1,"action":"Prepare data assessment","purpose":"Produce and validate data assessment","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare limitations","purpose":"Produce and validate limitations","depends_on":[2]... | [{"step":1,"action":"Prepare data assessment","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prep... | {"code":"calculation_mismatch","description":"A validation check found inconsistent results."} | [{"item":"data_assessment","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"limitations","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | test_data_decision | test | true | 1.0.0 | |
atm_0002015 | Design an automated workflow with dependencies, error handling and organized outputs. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an automated workflow with dependencies, error handling and organized outputs. Context: Some assumption... | ["workflow_automation","project_management","api_integration","file_management","backend_engineering"] | intermediate | recovered | ["testing_framework","email_client","file_manager","browser","code_editor"] | ["Explain uncertainty and missing information.","Respect dependencies between tasks.","Validate calculations before presenting conclusions."] | ["workflow_specification","dependency_map","error_policy","implementation_plan"] | [{"step":1,"action":"Prepare workflow specification","purpose":"Produce and validate workflow specification","depends_on":[]},{"step":2,"action":"Prepare dependency map","purpose":"Produce and validate dependency map","depends_on":[1]},{"step":3,"action":"Prepare error policy","purpose":"Produce and validate error poli... | [{"step":1,"action":"Prepare workflow specification","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare dependency map","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"st... | {"code":"test_failure","description":"A test did not meet its expected condition."} | [{"item":"workflow_specification","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"error_policy","check":"Check structure, completeness and consistency.","result":"s... | {"status":"recovered","completed_outputs":["workflow_specification","dependency_map","error_policy","implementation_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Report the remaining limitation if recovery is not possible.","Request the missing input from th... | business_automation | train | true | 1.0.0 | |
atm_0002016 | Inspect a software project, diagnose a reported problem, propose a correction and verify it. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Inspect a software project, diagnose a reported problem, propose a correction and verify it. Context: The user... | ["terminal_operations","debugging","software_testing","file_management","backend_engineering"] | very_complex | success | ["terminal","spreadsheet","testing_framework","api_client"] | ["Do not claim that an action succeeded without evidence.","Respect dependencies between tasks.","Avoid exposing credentials or private information.","Validate calculations before presenting conclusions.","Report errors instead of silently ignoring them."] | ["diagnosis","repair_plan","test_results","change_summary"] | [{"step":1,"action":"Prepare diagnosis","purpose":"Produce and validate diagnosis","depends_on":[]},{"step":2,"action":"Prepare repair plan","purpose":"Produce and validate repair plan","depends_on":[1]},{"step":3,"action":"Prepare test results","purpose":"Produce and validate test results","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare diagnosis","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare repair plan","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pr... | [{"item":"diagnosis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"repair_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"test_results","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"success","completed_outputs":["diagnosis","repair_plan","test_results","change_summary"],"message":"The planned outputs are represented as completed in this synthetic example."} | terminal_debugging | train | true | 1.0.0 | ||
atm_0002017 | Plan a small software product from requirements through implementation, testing and documentation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a small software product from requirements through implementation, testing and documentation. Context: Th... | ["document_creation","backend_engineering","software_testing","app_development","project_management","cross_domain_execution","decision_making","debugging"] | very_complex | failed | ["database","code_editor","terminal","testing_framework","file_manager","spreadsheet","email_client","browser"] | ["Validate calculations before presenting conclusions.","Do not claim that an action succeeded without evidence.","Preserve original source data.","Explain uncertainty and missing information."] | ["requirements","architecture","implementation_plan","test_report","documentation"] | [{"step":1,"action":"Prepare requirements","purpose":"Produce and validate requirements","depends_on":[]},{"step":2,"action":"Prepare architecture","purpose":"Produce and validate architecture","depends_on":[1]},{"step":3,"action":"Prepare implementation plan","purpose":"Produce and validate implementation plan","depen... | [{"step":1,"action":"Prepare requirements","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare architecture","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pre... | {"code":"permission_denied","description":"The requested operation lacks authorization."} | [{"item":"requirements","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"architecture","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"implementation_plan","check":"Check structure, completeness and consistency.","result":"simula... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | integrated_product | train | true | 1.0.0 | |
atm_0002018 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The task requires bot... | ["app_development","api_integration","backend_engineering","software_testing","database_management"] | intermediate | clarification | ["database","testing_framework","terminal","browser"] | ["Report errors instead of silently ignoring them.","Avoid exposing credentials or private information.","Explain uncertainty and missing information.","Do not claim that an action succeeded without evidence."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [] | What deadline should the plan follow? | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"needs_clarification","completed_outputs":[],"question":"What deadline should the plan follow?","message":"Pause consequential execution until the ambiguity is resolved."} | api_product | train | true | 1.0.0 | |
atm_0002019 | Evaluate information from multiple sources, identify uncertainty and create a concise report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Evaluate information from multiple sources, identify uncertainty and create a concise report. Context: The tas... | ["data_analysis","document_creation","research"] | advanced | success | ["browser","api_client","chart_generator","spreadsheet","file_manager","document_editor","database"] | ["Report errors instead of silently ignoring them.","Preserve original source data.","Avoid exposing credentials or private information."] | ["source_assessment","findings","uncertainties","report"] | [{"step":1,"action":"Prepare source assessment","purpose":"Produce and validate source assessment","depends_on":[]},{"step":2,"action":"Prepare findings","purpose":"Produce and validate findings","depends_on":[1]},{"step":3,"action":"Prepare uncertainties","purpose":"Produce and validate uncertainties","depends_on":[2]... | [{"step":1,"action":"Prepare source assessment","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare findings","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action"... | [{"item":"source_assessment","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"findings","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"uncertainties","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"success","completed_outputs":["source_assessment","findings","uncertainties","report"],"message":"The planned outputs are represented as completed in this synthetic example."} | validation_research | validation | true | 1.0.0 | ||
atm_0002020 | Organize a project workspace, inspect its contents and design a repeatable workflow. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Organize a project workspace, inspect its contents and design a repeatable workflow. Context: The task require... | ["terminal_operations","file_management","workflow_automation","decision_making","financial_analysis"] | intermediate | clarification | ["terminal","api_client","database","email_client"] | ["Explain uncertainty and missing information.","Avoid exposing credentials or private information.","Report errors instead of silently ignoring them.","Use accessible and understandable interfaces."] | ["workspace_map","workflow","validation_checks"] | [{"step":1,"action":"Prepare workspace map","purpose":"Produce and validate workspace map","depends_on":[]},{"step":2,"action":"Prepare workflow","purpose":"Produce and validate workflow","depends_on":[1]},{"step":3,"action":"Prepare validation checks","purpose":"Produce and validate validation checks","depends_on":[2]... | [{"step":1,"action":"Prepare workspace map","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Which source should be treated as authoritative? | [{"item":"workspace_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"workflow","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"validation_checks","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"needs_clarification","completed_outputs":[],"question":"Which source should be treated as authoritative?","message":"Pause consequential execution until the ambiguity is resolved."} | validation_operations | validation | true | 1.0.0 | |
atm_0002021 | Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. Context: The workf... | ["debugging","software_testing","project_management","terminal_operations","cross_domain_execution","financial_analysis"] | intermediate | impossible | ["terminal","api_client","file_manager","database"] | ["Explain uncertainty and missing information.","Report errors instead of silently ignoring them.","Avoid exposing credentials or private information.","Respect dependencies between tasks."] | ["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"] | [{"step":1,"action":"Prepare incident summary","purpose":"Produce and validate incident summary","depends_on":[]},{"step":2,"action":"Prepare root cause hypothesis","purpose":"Produce and validate root cause hypothesis","depends_on":[1]},{"step":3,"action":"Prepare recovery plan","purpose":"Produce and validate recover... | [{"step":1,"action":"Prepare incident summary","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare root cause hypothesis","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"actio... | [{"item":"incident_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"root_cause_hypothesis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"recovery_plan","check":"Check structure, completeness and consistency.","result":... | {"status":"impossible","completed_outputs":[],"reason":"The requested conclusion cannot be supported by the available evidence.","message":"Explain the limitation and identify a feasible alternative."} | test_recovery_workflow | test | true | 1.0.0 | ||
atm_0002022 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The task re... | ["email_writing","document_creation","research","decision_making","cross_domain_execution","software_testing"] | advanced | clarification | ["chart_generator","spreadsheet","email_client","python"] | ["Respect dependencies between tasks.","Explain uncertainty and missing information.","Use accessible and understandable interfaces."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Which source should be treated as authoritative? | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"needs_clarification","completed_outputs":[],"question":"Which source should be treated as authoritative?","message":"Pause consequential execution until the ambiguity is resolved."} | research_to_proposal | train | true | 1.0.0 | |
atm_0002023 | Inspect a software project, diagnose a reported problem, propose a correction and verify it. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Inspect a software project, diagnose a reported problem, propose a correction and verify it. Context: The avai... | ["software_testing","terminal_operations","debugging","file_management"] | very_complex | clarification | ["code_editor","python","email_client","database","api_client","document_editor"] | ["Explain uncertainty and missing information.","Validate calculations before presenting conclusions.","Preserve original source data."] | ["diagnosis","repair_plan","test_results","change_summary"] | [{"step":1,"action":"Prepare diagnosis","purpose":"Produce and validate diagnosis","depends_on":[]},{"step":2,"action":"Prepare repair plan","purpose":"Produce and validate repair plan","depends_on":[1]},{"step":3,"action":"Prepare test results","purpose":"Produce and validate test results","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare diagnosis","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare repair plan","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Which requirements are mandatory and which are optional? | [{"item":"diagnosis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"repair_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"test_results","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"needs_clarification","completed_outputs":[],"question":"Which requirements are mandatory and which are optional?","message":"Pause consequential execution until the ambiguity is resolved."} | terminal_debugging | train | true | 1.0.0 | |
atm_0002024 | Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. Context: The ... | ["decision_making","financial_analysis","data_analysis","document_creation","app_development","workflow_automation"] | advanced | failed | ["terminal","spreadsheet","testing_framework","browser","file_manager","document_editor"] | ["Keep outputs structured and easy to inspect.","Do not claim that an action succeeded without evidence.","Explain uncertainty and missing information.","Preserve original source data."] | ["assumptions","calculations","scenario_comparison","decision_report"] | [{"step":1,"action":"Prepare assumptions","purpose":"Produce and validate assumptions","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare scenario comparison","purpose":"Produce and validate scenario comparison","depends... | [{"step":1,"action":"Prepare assumptions","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare ... | {"code":"permission_denied","description":"The requested operation lacks authorization."} | [{"item":"assumptions","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"scenario_comparison","check":"Check structure, completeness and consistency.","result":"simulat... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | financial_decision | train | true | 1.0.0 | |
atm_0002025 | Evaluate information from multiple sources, identify uncertainty and create a concise report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Evaluate information from multiple sources, identify uncertainty and create a concise report. Context: The use... | ["data_analysis","research","document_creation"] | intermediate | recovered | ["chart_generator","spreadsheet","browser","email_client","python","database","testing_framework"] | ["Respect dependencies between tasks.","Do not claim that an action succeeded without evidence.","Preserve original source data.","Report errors instead of silently ignoring them.","Use accessible and understandable interfaces."] | ["source_assessment","findings","uncertainties","report"] | [{"step":1,"action":"Prepare source assessment","purpose":"Produce and validate source assessment","depends_on":[]},{"step":2,"action":"Prepare findings","purpose":"Produce and validate findings","depends_on":[1]},{"step":3,"action":"Prepare uncertainties","purpose":"Produce and validate uncertainties","depends_on":[2]... | [{"step":1,"action":"Prepare source assessment","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare findings","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pr... | {"code":"test_failure","description":"A test did not meet its expected condition."} | [{"item":"source_assessment","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"findings","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"uncertainties","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"recovered","completed_outputs":["source_assessment","findings","uncertainties","report"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Correct the issue and repeat the relevant validation.","Preserve the original data before attempting a correction.","Re... | validation_research | validation | true | 1.0.0 | |
atm_0002026 | Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. Context: The ... | ["decision_making","document_creation","financial_analysis","data_analysis"] | intermediate | clarification | ["database","spreadsheet","email_client","terminal","file_manager"] | ["Report errors instead of silently ignoring them.","Do not claim that an action succeeded without evidence.","Avoid exposing credentials or private information."] | ["assumptions","calculations","scenario_comparison","decision_report"] | [{"step":1,"action":"Prepare assumptions","purpose":"Produce and validate assumptions","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare scenario comparison","purpose":"Produce and validate scenario comparison","depends... | [{"step":1,"action":"Prepare assumptions","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Which requirements are mandatory and which are optional? | [{"item":"assumptions","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"scenario_comparison","check":"Check structure, completeness and consistency.","result":"simulat... | {"status":"needs_clarification","completed_outputs":[],"question":"Which requirements are mandatory and which are optional?","message":"Pause consequential execution until the ambiguity is resolved."} | financial_decision | train | true | 1.0.0 | |
atm_0002027 | Design an automated workflow with dependencies, error handling and organized outputs. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an automated workflow with dependencies, error handling and organized outputs. Context: The user expect... | ["file_management","api_integration","workflow_automation","project_management"] | intermediate | failed | ["database","email_client","document_editor","spreadsheet","terminal","python"] | ["Use accessible and understandable interfaces.","Validate calculations before presenting conclusions.","Respect dependencies between tasks.","Preserve original source data.","Explain uncertainty and missing information."] | ["workflow_specification","dependency_map","error_policy","implementation_plan"] | [{"step":1,"action":"Prepare workflow specification","purpose":"Produce and validate workflow specification","depends_on":[]},{"step":2,"action":"Prepare dependency map","purpose":"Produce and validate dependency map","depends_on":[1]},{"step":3,"action":"Prepare error policy","purpose":"Produce and validate error poli... | [{"step":1,"action":"Prepare workflow specification","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare dependency map","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,... | {"code":"dependency_error","description":"A required dependency is unavailable."} | [{"item":"workflow_specification","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"error_policy","check":"Check structure, completeness and consistency.","result":"s... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | business_automation | train | true | 1.0.0 | |
atm_0002028 | Plan a database migration with validation, rollback considerations and application compatibility. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a database migration with validation, rollback considerations and application compatibility. Context: The... | ["backend_engineering","terminal_operations","database_management","software_testing","file_management","project_management"] | very_complex | recovered | ["api_client","file_manager","code_editor","terminal","spreadsheet","chart_generator","browser","python"] | ["Preserve original source data.","Keep outputs structured and easy to inspect.","Use accessible and understandable interfaces.","Explain uncertainty and missing information.","Do not claim that an action succeeded without evidence."] | ["migration_plan","schema_changes","validation_checks","rollback_plan"] | [{"step":1,"action":"Prepare migration plan","purpose":"Produce and validate migration plan","depends_on":[]},{"step":2,"action":"Prepare schema changes","purpose":"Produce and validate schema changes","depends_on":[1]},{"step":3,"action":"Prepare validation checks","purpose":"Produce and validate validation checks","d... | [{"step":1,"action":"Prepare migration plan","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare schema changes","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pr... | {"code":"test_failure","description":"A test did not meet its expected condition."} | [{"item":"migration_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"schema_changes","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"validation_checks","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"recovered","completed_outputs":["migration_plan","schema_changes","validation_checks","rollback_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Use a documented alternative when authorized.","Inspect the failing component and isolate the cause.","Co... | database_migration | train | true | 1.0.0 | |
atm_0002029 | Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. Context: Seve... | ["financial_analysis","decision_making","data_analysis","document_creation","ui_ux_design"] | expert | success | ["spreadsheet","api_client","document_editor","chart_generator","python","testing_framework","code_editor"] | ["Do not claim that an action succeeded without evidence.","Validate calculations before presenting conclusions.","Avoid exposing credentials or private information.","Preserve original source data."] | ["assumptions","calculations","scenario_comparison","decision_report"] | [{"step":1,"action":"Prepare assumptions","purpose":"Produce and validate assumptions","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare scenario comparison","purpose":"Produce and validate scenario comparison","depends... | [{"step":1,"action":"Prepare assumptions","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"... | [{"item":"assumptions","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"scenario_comparison","check":"Check structure, completeness and consistency.","result":"simulat... | {"status":"success","completed_outputs":["assumptions","calculations","scenario_comparison","decision_report"],"message":"The planned outputs are represented as completed in this synthetic example."} | financial_decision | train | true | 1.0.0 | ||
atm_0002030 | Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. Context: The outpu... | ["project_management","debugging","software_testing","terminal_operations","cross_domain_execution","data_analysis","backend_engineering"] | advanced | failed | ["spreadsheet","browser","database","testing_framework","api_client"] | ["Respect dependencies between tasks.","Validate calculations before presenting conclusions.","Explain uncertainty and missing information.","Do not claim that an action succeeded without evidence.","Use accessible and understandable interfaces."] | ["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"] | [{"step":1,"action":"Prepare incident summary","purpose":"Produce and validate incident summary","depends_on":[]},{"step":2,"action":"Prepare root cause hypothesis","purpose":"Produce and validate root cause hypothesis","depends_on":[1]},{"step":3,"action":"Prepare recovery plan","purpose":"Produce and validate recover... | [{"step":1,"action":"Prepare incident summary","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare root cause hypothesis","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"actio... | {"code":"permission_denied","description":"The requested operation lacks authorization."} | [{"item":"incident_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"root_cause_hypothesis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"recovery_plan","check":"Check structure, completeness and consistency.","result":... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | test_recovery_workflow | test | true | 1.0.0 | |
atm_0002031 | Analyse financial records, calculate key indicators, produce a report and prepare a communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Analyse financial records, calculate key indicators, produce a report and prepare a communication. Context: Th... | ["document_creation","data_analysis","financial_analysis","email_writing","research"] | intermediate | success | ["code_editor","terminal","python","email_client"] | ["Do not claim that an action succeeded without evidence.","Respect dependencies between tasks.","Explain uncertainty and missing information.","Validate calculations before presenting conclusions.","Preserve original source data."] | ["validated_metrics","financial_report","executive_summary","email_draft"] | [{"step":1,"action":"Prepare validated metrics","purpose":"Produce and validate validated metrics","depends_on":[]},{"step":2,"action":"Prepare financial report","purpose":"Produce and validate financial report","depends_on":[1]},{"step":3,"action":"Prepare executive summary","purpose":"Produce and validate executive s... | [{"step":1,"action":"Prepare validated metrics","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare financial report","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action... | [{"item":"validated_metrics","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"financial_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"executive_summary","check":"Check structure, completeness and consistency.","result":... | {"status":"success","completed_outputs":["validated_metrics","financial_report","executive_summary","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | financial_reporting | train | true | 1.0.0 | ||
atm_0002032 | Design and implement a user-friendly application with a backend, database and verification plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design and implement a user-friendly application with a backend, database and verification plan. Context: Some... | ["app_development","database_management","backend_engineering","software_testing"] | expert | failed | ["python","spreadsheet","terminal","database","document_editor","browser"] | ["Report errors instead of silently ignoring them.","Validate calculations before presenting conclusions.","Use accessible and understandable interfaces.","Avoid exposing credentials or private information."] | ["application_design","backend_plan","database_schema","test_report"] | [{"step":1,"action":"Prepare application design","purpose":"Produce and validate application design","depends_on":[]},{"step":2,"action":"Prepare backend plan","purpose":"Produce and validate backend plan","depends_on":[1]},{"step":3,"action":"Prepare database schema","purpose":"Produce and validate database schema","d... | [{"step":1,"action":"Prepare application design","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend plan","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"... | {"code":"dependency_error","description":"A required dependency is unavailable."} | [{"item":"application_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"database_schema","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | fullstack_delivery | train | true | 1.0.0 | |
atm_0002033 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The user ex... | ["research","document_creation","decision_making","email_writing"] | advanced | success | ["chart_generator","email_client","file_manager","browser","spreadsheet"] | ["Validate calculations before presenting conclusions.","Keep outputs structured and easy to inspect.","Do not claim that an action succeeded without evidence.","Avoid exposing credentials or private information.","Report errors instead of silently ignoring them."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"P... | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"success","completed_outputs":["research_summary","comparison","proposal","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | research_to_proposal | train | true | 1.0.0 | ||
atm_0002034 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The workflo... | ["document_creation","email_writing","decision_making","research","database_management","data_analysis"] | very_complex | success | ["document_editor","browser","code_editor","email_client","chart_generator","terminal","python"] | ["Keep outputs structured and easy to inspect.","Do not claim that an action succeeded without evidence.","Explain uncertainty and missing information.","Preserve original source data.","Report errors instead of silently ignoring them."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action... | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"success","completed_outputs":["research_summary","comparison","proposal","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | research_to_proposal | train | true | 1.0.0 | ||
atm_0002035 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The available informa... | ["backend_engineering","software_testing","app_development","api_integration","decision_making","ui_ux_design","data_analysis"] | very_complex | impossible | ["browser","api_client","email_client","code_editor","python","file_manager"] | ["Report errors instead of silently ignoring them.","Avoid exposing credentials or private information.","Respect dependencies between tasks.","Preserve original source data.","Explain uncertainty and missing information."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepar... | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"impossible","completed_outputs":[],"reason":"The requested conclusion cannot be supported by the available evidence.","message":"Explain the limitation and identify a feasible alternative."} | api_product | train | true | 1.0.0 | ||
atm_0002036 | Collect source information, create structured documents and prepare organized deliverables. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Collect source information, create structured documents and prepare organized deliverables. Context: Several d... | ["document_creation","research","file_management","email_writing"] | expert | impossible | ["python","email_client","spreadsheet","database"] | ["Keep outputs structured and easy to inspect.","Use accessible and understandable interfaces.","Report errors instead of silently ignoring them.","Do not claim that an action succeeded without evidence."] | ["source_notes","main_document","file_index","email_draft"] | [{"step":1,"action":"Prepare source notes","purpose":"Produce and validate source notes","depends_on":[]},{"step":2,"action":"Prepare main document","purpose":"Produce and validate main document","depends_on":[1]},{"step":3,"action":"Prepare file index","purpose":"Produce and validate file index","depends_on":[2]},{"st... | [{"step":1,"action":"Prepare source notes","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | [{"item":"source_notes","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"main_document","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"file_index","check":"Check structure, completeness and consistency.","result":"simulated_chec... | {"status":"impossible","completed_outputs":[],"reason":"The requested conclusion cannot be supported by the available evidence.","message":"Explain the limitation and identify a feasible alternative."} | document_workflow | train | true | 1.0.0 | ||
atm_0002037 | Plan a database migration with validation, rollback considerations and application compatibility. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a database migration with validation, rollback considerations and application compatibility. Context: Som... | ["backend_engineering","terminal_operations","software_testing","database_management","api_integration","app_development"] | intermediate | recovered | ["file_manager","email_client","terminal","document_editor","spreadsheet","chart_generator","code_editor","database"] | ["Use accessible and understandable interfaces.","Report errors instead of silently ignoring them.","Validate calculations before presenting conclusions.","Do not claim that an action succeeded without evidence.","Avoid exposing credentials or private information."] | ["migration_plan","schema_changes","validation_checks","rollback_plan"] | [{"step":1,"action":"Prepare migration plan","purpose":"Produce and validate migration plan","depends_on":[]},{"step":2,"action":"Prepare schema changes","purpose":"Produce and validate schema changes","depends_on":[1]},{"step":3,"action":"Prepare validation checks","purpose":"Produce and validate validation checks","d... | [{"step":1,"action":"Prepare migration plan","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare schema changes","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action"... | {"code":"dependency_error","description":"A required dependency is unavailable."} | [{"item":"migration_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"schema_changes","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"validation_checks","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"recovered","completed_outputs":["migration_plan","schema_changes","validation_checks","rollback_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Request the missing input from the user.","Preserve the original data before attempting a correction.","I... | database_migration | train | true | 1.0.0 | |
atm_0002038 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The outputs must be o... | ["api_integration","software_testing","app_development","backend_engineering"] | intermediate | impossible | ["python","api_client","terminal","chart_generator","browser","testing_framework","email_client"] | ["Respect dependencies between tasks.","Validate calculations before presenting conclusions.","Preserve original source data.","Report errors instead of silently ignoring them.","Explain uncertainty and missing information."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"impossible","completed_outputs":[],"reason":"The requested outputs contradict a stated constraint.","message":"Explain the limitation and identify a feasible alternative."} | api_product | train | true | 1.0.0 | ||
atm_0002039 | Plan a small software product from requirements through implementation, testing and documentation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a small software product from requirements through implementation, testing and documentation. Context: Th... | ["document_creation","app_development","project_management","software_testing","backend_engineering","terminal_operations"] | intermediate | failed | ["python","file_manager","document_editor","terminal","chart_generator","api_client","code_editor","spreadsheet"] | ["Validate calculations before presenting conclusions.","Explain uncertainty and missing information.","Keep outputs structured and easy to inspect.","Do not claim that an action succeeded without evidence."] | ["requirements","architecture","implementation_plan","test_report","documentation"] | [{"step":1,"action":"Prepare requirements","purpose":"Produce and validate requirements","depends_on":[]},{"step":2,"action":"Prepare architecture","purpose":"Produce and validate architecture","depends_on":[1]},{"step":3,"action":"Prepare implementation plan","purpose":"Produce and validate implementation plan","depen... | [{"step":1,"action":"Prepare requirements","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare architecture","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":... | {"code":"dependency_error","description":"A required dependency is unavailable."} | [{"item":"requirements","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"architecture","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"implementation_plan","check":"Check structure, completeness and consistency.","result":"simula... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | integrated_product | train | true | 1.0.0 | |
atm_0002040 | Analyse financial records, calculate key indicators, produce a report and prepare a communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Analyse financial records, calculate key indicators, produce a report and prepare a communication. Context: Th... | ["financial_analysis","data_analysis","document_creation","email_writing","file_management","workflow_automation","api_integration"] | very_complex | success | ["database","python","spreadsheet","code_editor","chart_generator"] | ["Preserve original source data.","Explain uncertainty and missing information.","Validate calculations before presenting conclusions.","Avoid exposing credentials or private information."] | ["validated_metrics","financial_report","executive_summary","email_draft"] | [{"step":1,"action":"Prepare validated metrics","purpose":"Produce and validate validated metrics","depends_on":[]},{"step":2,"action":"Prepare financial report","purpose":"Produce and validate financial report","depends_on":[1]},{"step":3,"action":"Prepare executive summary","purpose":"Produce and validate executive s... | [{"step":1,"action":"Prepare validated metrics","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare financial report","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action... | [{"item":"validated_metrics","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"financial_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"executive_summary","check":"Check structure, completeness and consistency.","result":... | {"status":"success","completed_outputs":["validated_metrics","financial_report","executive_summary","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | financial_reporting | train | true | 1.0.0 | ||
atm_0002041 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The user expects clea... | ["software_testing","app_development","api_integration","backend_engineering"] | very_complex | clarification | ["document_editor","python","database","api_client","file_manager","spreadsheet","terminal","chart_generator"] | ["Preserve original source data.","Validate calculations before presenting conclusions.","Do not claim that an action succeeded without evidence."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Should the application be designed for desktop, mobile or both? | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"needs_clarification","completed_outputs":[],"question":"Should the application be designed for desktop, mobile or both?","message":"Pause consequential execution until the ambiguity is resolved."} | api_product | train | true | 1.0.0 | |
atm_0002042 | Analyse financial records, calculate key indicators, produce a report and prepare a communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Analyse financial records, calculate key indicators, produce a report and prepare a communication. Context: Th... | ["data_analysis","email_writing","document_creation","financial_analysis","software_testing"] | expert | clarification | ["database","api_client","document_editor","testing_framework","terminal","browser","email_client","chart_generator"] | ["Keep outputs structured and easy to inspect.","Explain uncertainty and missing information.","Use accessible and understandable interfaces."] | ["validated_metrics","financial_report","executive_summary","email_draft"] | [{"step":1,"action":"Prepare validated metrics","purpose":"Produce and validate validated metrics","depends_on":[]},{"step":2,"action":"Prepare financial report","purpose":"Produce and validate financial report","depends_on":[1]},{"step":3,"action":"Prepare executive summary","purpose":"Produce and validate executive s... | [{"step":1,"action":"Prepare validated metrics","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare financial report","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3... | What deadline should the plan follow? | [{"item":"validated_metrics","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"financial_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"executive_summary","check":"Check structure, completeness and consistency.","result":... | {"status":"needs_clarification","completed_outputs":[],"question":"What deadline should the plan follow?","message":"Pause consequential execution until the ambiguity is resolved."} | financial_reporting | train | true | 1.0.0 | |
atm_0002043 | Interpret unfamiliar structured data, document limitations and prepare a reasoned recommendation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Interpret unfamiliar structured data, document limitations and prepare a reasoned recommendation. Context: The... | ["decision_making","data_analysis","document_creation","financial_analysis","research","database_management"] | very_complex | success | ["chart_generator","database","spreadsheet","email_client","testing_framework"] | ["Explain uncertainty and missing information.","Avoid exposing credentials or private information.","Preserve original source data."] | ["data_assessment","calculations","limitations","recommendation"] | [{"step":1,"action":"Prepare data assessment","purpose":"Produce and validate data assessment","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare limitations","purpose":"Produce and validate limitations","depends_on":[2]... | [{"step":1,"action":"Prepare data assessment","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"actio... | [{"item":"data_assessment","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"limitations","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"success","completed_outputs":["data_assessment","calculations","limitations","recommendation"],"message":"The planned outputs are represented as completed in this synthetic example."} | test_data_decision | test | true | 1.0.0 | ||
atm_0002044 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: Some assumptions need... | ["backend_engineering","software_testing","api_integration","app_development","data_analysis","project_management","decision_making"] | advanced | recovered | ["spreadsheet","terminal","document_editor","database","python","chart_generator"] | ["Validate calculations before presenting conclusions.","Avoid exposing credentials or private information.","Explain uncertainty and missing information."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pr... | {"code":"missing_input","description":"A required input is missing."} | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"recovered","completed_outputs":["api_contract","backend_design","interface_spec","test_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Inspect the failing component and isolate the cause.","Use a documented alternative when authorized."]} | api_product | train | true | 1.0.0 | |
atm_0002045 | Plan a small software product from requirements through implementation, testing and documentation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a small software product from requirements through implementation, testing and documentation. Context: So... | ["backend_engineering","app_development","project_management","document_creation","software_testing","data_analysis","cross_domain_execution","workflow_automation"] | intermediate | impossible | ["document_editor","file_manager","api_client","chart_generator","testing_framework"] | ["Keep outputs structured and easy to inspect.","Do not claim that an action succeeded without evidence.","Preserve original source data.","Avoid exposing credentials or private information.","Use accessible and understandable interfaces."] | ["requirements","architecture","implementation_plan","test_report","documentation"] | [{"step":1,"action":"Prepare requirements","purpose":"Produce and validate requirements","depends_on":[]},{"step":2,"action":"Prepare architecture","purpose":"Produce and validate architecture","depends_on":[1]},{"step":3,"action":"Prepare implementation plan","purpose":"Produce and validate implementation plan","depen... | [{"step":1,"action":"Prepare requirements","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare architecture","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | [{"item":"requirements","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"architecture","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"implementation_plan","check":"Check structure, completeness and consistency.","result":"simula... | {"status":"impossible","completed_outputs":[],"reason":"The requested outputs contradict a stated constraint.","message":"Explain the limitation and identify a feasible alternative."} | integrated_product | train | true | 1.0.0 | ||
atm_0002046 | Design an automated workflow with dependencies, error handling and organized outputs. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an automated workflow with dependencies, error handling and organized outputs. Context: The task requir... | ["project_management","api_integration","workflow_automation","file_management"] | expert | success | ["database","testing_framework","python","chart_generator","spreadsheet"] | ["Respect dependencies between tasks.","Keep outputs structured and easy to inspect.","Do not claim that an action succeeded without evidence.","Validate calculations before presenting conclusions."] | ["workflow_specification","dependency_map","error_policy","implementation_plan"] | [{"step":1,"action":"Prepare workflow specification","purpose":"Produce and validate workflow specification","depends_on":[]},{"step":2,"action":"Prepare dependency map","purpose":"Produce and validate dependency map","depends_on":[1]},{"step":3,"action":"Prepare error policy","purpose":"Produce and validate error poli... | [{"step":1,"action":"Prepare workflow specification","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare dependency map","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action... | [{"item":"workflow_specification","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"error_policy","check":"Check structure, completeness and consistency.","result":"s... | {"status":"success","completed_outputs":["workflow_specification","dependency_map","error_policy","implementation_plan"],"message":"The planned outputs are represented as completed in this synthetic example."} | business_automation | train | true | 1.0.0 | ||
atm_0002047 | Evaluate an application concept, identify usability issues and propose testable improvements. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Evaluate an application concept, identify usability issues and propose testable improvements. Context: Some as... | ["ui_ux_design","software_testing","app_development","cross_domain_execution","financial_analysis"] | intermediate | recovered | ["spreadsheet","testing_framework","python","chart_generator","file_manager","database","email_client"] | ["Validate calculations before presenting conclusions.","Explain uncertainty and missing information.","Preserve original source data.","Use accessible and understandable interfaces.","Avoid exposing credentials or private information."] | ["ux_review","issue_list","improvements","test_plan"] | [{"step":1,"action":"Prepare ux review","purpose":"Produce and validate ux review","depends_on":[]},{"step":2,"action":"Prepare issue list","purpose":"Produce and validate issue list","depends_on":[1]},{"step":3,"action":"Prepare improvements","purpose":"Produce and validate improvements","depends_on":[2]},{"step":4,"a... | [{"step":1,"action":"Prepare ux review","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare issue list","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare... | {"code":"unavailable_service","description":"An external service cannot be confirmed as available."} | [{"item":"ux_review","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"issue_list","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"improvements","check":"Check structure, completeness and consistency.","result":"simulated_check"},... | {"status":"recovered","completed_outputs":["ux_review","issue_list","improvements","test_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Preserve the original data before attempting a correction.","Report the remaining limitation if recovery is not possible."]... | validation_application | validation | true | 1.0.0 | |
atm_0002048 | Evaluate an application concept, identify usability issues and propose testable improvements. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Evaluate an application concept, identify usability issues and propose testable improvements. Context: Some as... | ["ui_ux_design","app_development","software_testing","research","terminal_operations"] | intermediate | recovered | ["file_manager","database","api_client","testing_framework","spreadsheet","code_editor","chart_generator","browser"] | ["Report errors instead of silently ignoring them.","Keep outputs structured and easy to inspect.","Use accessible and understandable interfaces."] | ["ux_review","issue_list","improvements","test_plan"] | [{"step":1,"action":"Prepare ux review","purpose":"Produce and validate ux review","depends_on":[]},{"step":2,"action":"Prepare issue list","purpose":"Produce and validate issue list","depends_on":[1]},{"step":3,"action":"Prepare improvements","purpose":"Produce and validate improvements","depends_on":[2]},{"step":4,"a... | [{"step":1,"action":"Prepare ux review","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare issue list","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare improve... | {"code":"invalid_format","description":"An input file has an unexpected format."} | [{"item":"ux_review","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"issue_list","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"improvements","check":"Check structure, completeness and consistency.","result":"simulated_check"},... | {"status":"recovered","completed_outputs":["ux_review","issue_list","improvements","test_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Preserve the original data before attempting a correction.","Inspect the failing component and isolate the cause.","Report ... | validation_application | validation | true | 1.0.0 | |
atm_0002049 | Organize a project workspace, inspect its contents and design a repeatable workflow. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Organize a project workspace, inspect its contents and design a repeatable workflow. Context: Some assumptions... | ["terminal_operations","workflow_automation","file_management","financial_analysis","app_development","api_integration"] | expert | recovered | ["terminal","spreadsheet","python","email_client"] | ["Respect dependencies between tasks.","Preserve original source data.","Validate calculations before presenting conclusions."] | ["workspace_map","workflow","validation_checks"] | [{"step":1,"action":"Prepare workspace map","purpose":"Produce and validate workspace map","depends_on":[]},{"step":2,"action":"Prepare workflow","purpose":"Produce and validate workflow","depends_on":[1]},{"step":3,"action":"Prepare validation checks","purpose":"Produce and validate validation checks","depends_on":[2]... | [{"step":1,"action":"Prepare workspace map","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare workflow","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare val... | {"code":"unavailable_service","description":"An external service cannot be confirmed as available."} | [{"item":"workspace_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"workflow","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"validation_checks","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"recovered","completed_outputs":["workspace_map","workflow","validation_checks"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Preserve the original data before attempting a correction.","Inspect the failing component and isolate the cause.","Correct the ... | validation_operations | validation | true | 1.0.0 | |
atm_0002050 | Design and implement a user-friendly application with a backend, database and verification plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design and implement a user-friendly application with a backend, database and verification plan. Context: Seve... | ["software_testing","database_management","app_development","backend_engineering"] | advanced | success | ["chart_generator","document_editor","api_client","testing_framework","database"] | ["Explain uncertainty and missing information.","Keep outputs structured and easy to inspect.","Respect dependencies between tasks.","Validate calculations before presenting conclusions.","Report errors instead of silently ignoring them."] | ["application_design","backend_plan","database_schema","test_report"] | [{"step":1,"action":"Prepare application design","purpose":"Produce and validate application design","depends_on":[]},{"step":2,"action":"Prepare backend plan","purpose":"Produce and validate backend plan","depends_on":[1]},{"step":3,"action":"Prepare database schema","purpose":"Produce and validate database schema","d... | [{"step":1,"action":"Prepare application design","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend plan","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"actio... | [{"item":"application_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"database_schema","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"success","completed_outputs":["application_design","backend_plan","database_schema","test_report"],"message":"The planned outputs are represented as completed in this synthetic example."} | fullstack_delivery | train | true | 1.0.0 | ||
atm_0002051 | Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. Context: Some assu... | ["debugging","software_testing","terminal_operations","project_management"] | expert | success | ["api_client","database","testing_framework","chart_generator","browser","code_editor","spreadsheet"] | ["Respect dependencies between tasks.","Explain uncertainty and missing information.","Avoid exposing credentials or private information.","Preserve original source data.","Validate calculations before presenting conclusions."] | ["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"] | [{"step":1,"action":"Prepare incident summary","purpose":"Produce and validate incident summary","depends_on":[]},{"step":2,"action":"Prepare root cause hypothesis","purpose":"Produce and validate root cause hypothesis","depends_on":[1]},{"step":3,"action":"Prepare recovery plan","purpose":"Produce and validate recover... | [{"step":1,"action":"Prepare incident summary","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare root cause hypothesis","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step... | [{"item":"incident_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"root_cause_hypothesis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"recovery_plan","check":"Check structure, completeness and consistency.","result":... | {"status":"success","completed_outputs":["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"],"message":"The planned outputs are represented as completed in this synthetic example."} | test_recovery_workflow | test | true | 1.0.0 | ||
atm_0002052 | Plan a small software product from requirements through implementation, testing and documentation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a small software product from requirements through implementation, testing and documentation. Context: Se... | ["document_creation","project_management","app_development","backend_engineering","software_testing"] | advanced | success | ["document_editor","testing_framework","browser","python"] | ["Preserve original source data.","Do not claim that an action succeeded without evidence.","Avoid exposing credentials or private information.","Explain uncertainty and missing information."] | ["requirements","architecture","implementation_plan","test_report","documentation"] | [{"step":1,"action":"Prepare requirements","purpose":"Produce and validate requirements","depends_on":[]},{"step":2,"action":"Prepare architecture","purpose":"Produce and validate architecture","depends_on":[1]},{"step":3,"action":"Prepare implementation plan","purpose":"Produce and validate implementation plan","depen... | [{"step":1,"action":"Prepare requirements","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare architecture","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pr... | [{"item":"requirements","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"architecture","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"implementation_plan","check":"Check structure, completeness and consistency.","result":"simula... | {"status":"success","completed_outputs":["requirements","architecture","implementation_plan","test_report","documentation"],"message":"The planned outputs are represented as completed in this synthetic example."} | integrated_product | train | true | 1.0.0 | ||
atm_0002053 | Interpret unfamiliar structured data, document limitations and prepare a reasoned recommendation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Interpret unfamiliar structured data, document limitations and prepare a reasoned recommendation. Context: The... | ["data_analysis","decision_making","document_creation","financial_analysis","workflow_automation","database_management","app_development"] | intermediate | failed | ["email_client","terminal","chart_generator","api_client","python"] | ["Validate calculations before presenting conclusions.","Report errors instead of silently ignoring them.","Respect dependencies between tasks.","Do not claim that an action succeeded without evidence."] | ["data_assessment","calculations","limitations","recommendation"] | [{"step":1,"action":"Prepare data assessment","purpose":"Produce and validate data assessment","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare limitations","purpose":"Produce and validate limitations","depends_on":[2]... | [{"step":1,"action":"Prepare data assessment","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"... | {"code":"missing_input","description":"A required input is missing."} | [{"item":"data_assessment","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"limitations","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | test_data_decision | test | true | 1.0.0 | |
atm_0002054 | Transform a dataset into a dashboard with clear visualizations and a supporting data service. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Transform a dataset into a dashboard with clear visualizations and a supporting data service. Context: The pro... | ["data_analysis","ui_ux_design","backend_engineering","app_development","file_management","terminal_operations","project_management"] | expert | success | ["browser","python","file_manager","code_editor","terminal","document_editor","chart_generator","spreadsheet"] | ["Do not claim that an action succeeded without evidence.","Report errors instead of silently ignoring them.","Preserve original source data."] | ["data_quality_report","dashboard_spec","backend_design","verification_plan"] | [{"step":1,"action":"Prepare data quality report","purpose":"Produce and validate data quality report","depends_on":[]},{"step":2,"action":"Prepare dashboard spec","purpose":"Produce and validate dashboard spec","depends_on":[1]},{"step":3,"action":"Prepare backend design","purpose":"Produce and validate backend design... | [{"step":1,"action":"Prepare data quality report","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare dashboard spec","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,... | [{"item":"data_quality_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dashboard_spec","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"si... | {"status":"success","completed_outputs":["data_quality_report","dashboard_spec","backend_design","verification_plan"],"message":"The planned outputs are represented as completed in this synthetic example."} | data_dashboard | train | true | 1.0.0 | ||
atm_0002055 | Coordinate a project with deadlines, dependencies, stakeholders and documented decisions. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Coordinate a project with deadlines, dependencies, stakeholders and documented decisions. Context: The outputs... | ["email_writing","document_creation","decision_making","project_management"] | very_complex | success | ["python","terminal","browser","document_editor"] | ["Keep outputs structured and easy to inspect.","Report errors instead of silently ignoring them.","Validate calculations before presenting conclusions.","Respect dependencies between tasks."] | ["project_plan","timeline","decision_log","communications"] | [{"step":1,"action":"Prepare project plan","purpose":"Produce and validate project plan","depends_on":[]},{"step":2,"action":"Prepare timeline","purpose":"Produce and validate timeline","depends_on":[1]},{"step":3,"action":"Prepare decision log","purpose":"Produce and validate decision log","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare project plan","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare timeline","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare decision... | [{"item":"project_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"timeline","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"decision_log","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"success","completed_outputs":["project_plan","timeline","decision_log","communications"],"message":"The planned outputs are represented as completed in this synthetic example."} | project_coordination | train | true | 1.0.0 | ||
atm_0002056 | Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. Context: The ... | ["financial_analysis","document_creation","decision_making","data_analysis","email_writing","project_management","terminal_operations"] | very_complex | recovered | ["terminal","browser","code_editor","email_client","testing_framework","chart_generator"] | ["Explain uncertainty and missing information.","Keep outputs structured and easy to inspect.","Respect dependencies between tasks.","Use accessible and understandable interfaces."] | ["assumptions","calculations","scenario_comparison","decision_report"] | [{"step":1,"action":"Prepare assumptions","purpose":"Produce and validate assumptions","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare scenario comparison","purpose":"Produce and validate scenario comparison","depends... | [{"step":1,"action":"Prepare assumptions","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare calculations","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"act... | {"code":"dependency_error","description":"A required dependency is unavailable."} | [{"item":"assumptions","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"scenario_comparison","check":"Check structure, completeness and consistency.","result":"simulat... | {"status":"recovered","completed_outputs":["assumptions","calculations","scenario_comparison","decision_report"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Preserve the original data before attempting a correction.","Request the missing input from the user.","Us... | financial_decision | train | true | 1.0.0 | |
atm_0002057 | Design and implement a user-friendly application with a backend, database and verification plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design and implement a user-friendly application with a backend, database and verification plan. Context: Seve... | ["database_management","software_testing","backend_engineering","app_development","debugging"] | intermediate | success | ["chart_generator","document_editor","api_client","file_manager","database","spreadsheet","terminal"] | ["Explain uncertainty and missing information.","Validate calculations before presenting conclusions.","Keep outputs structured and easy to inspect.","Report errors instead of silently ignoring them."] | ["application_design","backend_plan","database_schema","test_report"] | [{"step":1,"action":"Prepare application design","purpose":"Produce and validate application design","depends_on":[]},{"step":2,"action":"Prepare backend plan","purpose":"Produce and validate backend plan","depends_on":[1]},{"step":3,"action":"Prepare database schema","purpose":"Produce and validate database schema","d... | [{"step":1,"action":"Prepare application design","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend plan","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"actio... | [{"item":"application_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"database_schema","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"success","completed_outputs":["application_design","backend_plan","database_schema","test_report"],"message":"The planned outputs are represented as completed in this synthetic example."} | fullstack_delivery | train | true | 1.0.0 | ||
atm_0002058 | Plan a small software product from requirements through implementation, testing and documentation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a small software product from requirements through implementation, testing and documentation. Context: Th... | ["app_development","software_testing","project_management","document_creation","backend_engineering","financial_analysis","decision_making","terminal_operations"] | advanced | success | ["api_client","spreadsheet","browser","file_manager","code_editor","database"] | ["Keep outputs structured and easy to inspect.","Avoid exposing credentials or private information.","Preserve original source data."] | ["requirements","architecture","implementation_plan","test_report","documentation"] | [{"step":1,"action":"Prepare requirements","purpose":"Produce and validate requirements","depends_on":[]},{"step":2,"action":"Prepare architecture","purpose":"Produce and validate architecture","depends_on":[1]},{"step":3,"action":"Prepare implementation plan","purpose":"Produce and validate implementation plan","depen... | [{"step":1,"action":"Prepare requirements","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare architecture","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pr... | [{"item":"requirements","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"architecture","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"implementation_plan","check":"Check structure, completeness and consistency.","result":"simula... | {"status":"success","completed_outputs":["requirements","architecture","implementation_plan","test_report","documentation"],"message":"The planned outputs are represented as completed in this synthetic example."} | integrated_product | train | true | 1.0.0 | ||
atm_0002059 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The task re... | ["research","decision_making","email_writing","document_creation","workflow_automation","app_development"] | advanced | recovered | ["document_editor","testing_framework","chart_generator","terminal","api_client","python","file_manager","code_editor"] | ["Respect dependencies between tasks.","Validate calculations before presenting conclusions.","Do not claim that an action succeeded without evidence.","Use accessible and understandable interfaces."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepar... | {"code":"calculation_mismatch","description":"A validation check found inconsistent results."} | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"recovered","completed_outputs":["research_summary","comparison","proposal","email_draft"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Use a documented alternative when authorized.","Request the missing input from the user."]} | research_to_proposal | train | true | 1.0.0 | |
atm_0002060 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: Some assumptions need... | ["backend_engineering","app_development","api_integration","software_testing","workflow_automation","decision_making","data_analysis"] | expert | recovered | ["browser","python","testing_framework","file_manager","database","email_client","chart_generator","code_editor"] | ["Keep outputs structured and easy to inspect.","Respect dependencies between tasks.","Preserve original source data.","Avoid exposing credentials or private information."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare int... | {"code":"invalid_format","description":"An input file has an unexpected format."} | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"recovered","completed_outputs":["api_contract","backend_design","interface_spec","test_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Report the remaining limitation if recovery is not possible.","Request the missing input from the user.","Preserve... | api_product | train | true | 1.0.0 | |
atm_0002061 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The workflo... | ["research","decision_making","email_writing","document_creation"] | advanced | failed | ["document_editor","api_client","file_manager","code_editor","python","testing_framework","spreadsheet"] | ["Preserve original source data.","Avoid exposing credentials or private information.","Keep outputs structured and easy to inspect.","Validate calculations before presenting conclusions.","Explain uncertainty and missing information."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action... | {"code":"invalid_format","description":"An input file has an unexpected format."} | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | research_to_proposal | train | true | 1.0.0 | |
atm_0002062 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The workflow should a... | ["software_testing","app_development","backend_engineering","api_integration"] | expert | clarification | ["spreadsheet","api_client","testing_framework","browser"] | ["Avoid exposing credentials or private information.","Use accessible and understandable interfaces.","Explain uncertainty and missing information."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"spreadsheet","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"acti... | Which requirements are mandatory and which are optional? | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"needs_clarification","completed_outputs":[],"question":"Which requirements are mandatory and which are optional?","message":"Pause consequential execution until the ambiguity is resolved."} | api_product | train | true | 1.0.0 | |
atm_0002063 | Organize a project workspace, inspect its contents and design a repeatable workflow. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Organize a project workspace, inspect its contents and design a repeatable workflow. Context: The project has ... | ["file_management","terminal_operations","workflow_automation","financial_analysis","debugging","ui_ux_design"] | advanced | success | ["email_client","chart_generator","database","document_editor"] | ["Report errors instead of silently ignoring them.","Avoid exposing credentials or private information.","Validate calculations before presenting conclusions."] | ["workspace_map","workflow","validation_checks"] | [{"step":1,"action":"Prepare workspace map","purpose":"Produce and validate workspace map","depends_on":[]},{"step":2,"action":"Prepare workflow","purpose":"Produce and validate workflow","depends_on":[1]},{"step":3,"action":"Prepare validation checks","purpose":"Produce and validate validation checks","depends_on":[2]... | [{"step":1,"action":"Prepare workspace map","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare workflow","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"P... | [{"item":"workspace_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"workflow","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"validation_checks","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"success","completed_outputs":["workspace_map","workflow","validation_checks"],"message":"The planned outputs are represented as completed in this synthetic example."} | validation_operations | validation | true | 1.0.0 | ||
atm_0002064 | Collect source information, create structured documents and prepare organized deliverables. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Collect source information, create structured documents and prepare organized deliverables. Context: The proje... | ["email_writing","file_management","research","document_creation"] | expert | recovered | ["terminal","email_client","spreadsheet","database","browser"] | ["Validate calculations before presenting conclusions.","Explain uncertainty and missing information.","Respect dependencies between tasks."] | ["source_notes","main_document","file_index","email_draft"] | [{"step":1,"action":"Prepare source notes","purpose":"Produce and validate source notes","depends_on":[]},{"step":2,"action":"Prepare main document","purpose":"Produce and validate main document","depends_on":[1]},{"step":3,"action":"Prepare file index","purpose":"Produce and validate file index","depends_on":[2]},{"st... | [{"step":1,"action":"Prepare source notes","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare main document","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare ... | {"code":"missing_input","description":"A required input is missing."} | [{"item":"source_notes","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"main_document","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"file_index","check":"Check structure, completeness and consistency.","result":"simulated_chec... | {"status":"recovered","completed_outputs":["source_notes","main_document","file_index","email_draft"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Inspect the failing component and isolate the cause.","Use a documented alternative when authorized.","Correct the is... | document_workflow | train | true | 1.0.0 | |
atm_0002065 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The project has a lim... | ["app_development","backend_engineering","software_testing","api_integration","workflow_automation","project_management","database_management"] | intermediate | recovered | ["code_editor","testing_framework","api_client","browser","file_manager"] | ["Explain uncertainty and missing information.","Do not claim that an action succeeded without evidence.","Use accessible and understandable interfaces.","Preserve original source data."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":... | {"code":"invalid_format","description":"An input file has an unexpected format."} | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"recovered","completed_outputs":["api_contract","backend_design","interface_spec","test_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Report the remaining limitation if recovery is not possible.","Inspect the failing component and isolate the cause... | api_product | train | true | 1.0.0 | |
atm_0002066 | Analyse financial records, calculate key indicators, produce a report and prepare a communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Analyse financial records, calculate key indicators, produce a report and prepare a communication. Context: Th... | ["email_writing","document_creation","data_analysis","financial_analysis","project_management","api_integration","cross_domain_execution"] | expert | clarification | ["api_client","database","code_editor","email_client","browser","terminal","spreadsheet","python"] | ["Preserve original source data.","Avoid exposing credentials or private information.","Explain uncertainty and missing information.","Report errors instead of silently ignoring them.","Keep outputs structured and easy to inspect."] | ["validated_metrics","financial_report","executive_summary","email_draft"] | [{"step":1,"action":"Prepare validated metrics","purpose":"Produce and validate validated metrics","depends_on":[]},{"step":2,"action":"Prepare financial report","purpose":"Produce and validate financial report","depends_on":[1]},{"step":3,"action":"Prepare executive summary","purpose":"Produce and validate executive s... | [{"step":1,"action":"Prepare validated metrics","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare financial report","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action"... | Which source should be treated as authoritative? | [{"item":"validated_metrics","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"financial_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"executive_summary","check":"Check structure, completeness and consistency.","result":... | {"status":"needs_clarification","completed_outputs":[],"question":"Which source should be treated as authoritative?","message":"Pause consequential execution until the ambiguity is resolved."} | financial_reporting | train | true | 1.0.0 | |
atm_0002067 | Plan a small software product from requirements through implementation, testing and documentation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a small software product from requirements through implementation, testing and documentation. Context: Th... | ["document_creation","software_testing","app_development","project_management","backend_engineering"] | advanced | recovered | ["testing_framework","document_editor","terminal","python","file_manager","code_editor","database","spreadsheet"] | ["Keep outputs structured and easy to inspect.","Avoid exposing credentials or private information.","Explain uncertainty and missing information."] | ["requirements","architecture","implementation_plan","test_report","documentation"] | [{"step":1,"action":"Prepare requirements","purpose":"Produce and validate requirements","depends_on":[]},{"step":2,"action":"Prepare architecture","purpose":"Produce and validate architecture","depends_on":[1]},{"step":3,"action":"Prepare implementation plan","purpose":"Produce and validate implementation plan","depen... | [{"step":1,"action":"Prepare requirements","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare architecture","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"ac... | {"code":"invalid_format","description":"An input file has an unexpected format."} | [{"item":"requirements","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"architecture","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"implementation_plan","check":"Check structure, completeness and consistency.","result":"simula... | {"status":"recovered","completed_outputs":["requirements","architecture","implementation_plan","test_report","documentation"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Inspect the failing component and isolate the cause.","Use a documented alternative when auth... | integrated_product | train | true | 1.0.0 | |
atm_0002068 | Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. Context: The ... | ["decision_making","data_analysis","financial_analysis","document_creation"] | advanced | clarification | ["testing_framework","document_editor","terminal","api_client","browser","email_client","code_editor"] | ["Validate calculations before presenting conclusions.","Keep outputs structured and easy to inspect.","Respect dependencies between tasks."] | ["assumptions","calculations","scenario_comparison","decision_report"] | [{"step":1,"action":"Prepare assumptions","purpose":"Produce and validate assumptions","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare scenario comparison","purpose":"Produce and validate scenario comparison","depends... | [{"step":1,"action":"Prepare assumptions","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Which source should be treated as authoritative? | [{"item":"assumptions","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"scenario_comparison","check":"Check structure, completeness and consistency.","result":"simulat... | {"status":"needs_clarification","completed_outputs":[],"question":"Which source should be treated as authoritative?","message":"Pause consequential execution until the ambiguity is resolved."} | financial_decision | train | true | 1.0.0 | |
atm_0002069 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The user ex... | ["document_creation","email_writing","research","decision_making"] | intermediate | recovered | ["python","document_editor","terminal","chart_generator","database","file_manager","testing_framework","api_client"] | ["Do not claim that an action succeeded without evidence.","Validate calculations before presenting conclusions.","Report errors instead of silently ignoring them.","Preserve original source data."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare p... | {"code":"invalid_format","description":"An input file has an unexpected format."} | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"recovered","completed_outputs":["research_summary","comparison","proposal","email_draft"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Report the remaining limitation if recovery is not possible.","Preserve the original data before attempting a correcti... | research_to_proposal | train | true | 1.0.0 | |
atm_0002070 | Coordinate a complex application delivery with technical dependencies and stakeholder communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Coordinate a complex application delivery with technical dependencies and stakeholder communication. Context: ... | ["app_development","project_management","backend_engineering","email_writing"] | advanced | success | ["email_client","code_editor","database","chart_generator","document_editor","spreadsheet","python","testing_framework"] | ["Avoid exposing credentials or private information.","Validate calculations before presenting conclusions.","Respect dependencies between tasks."] | ["delivery_plan","technical_design","dependency_report","email_draft"] | [{"step":1,"action":"Prepare delivery plan","purpose":"Produce and validate delivery plan","depends_on":[]},{"step":2,"action":"Prepare technical design","purpose":"Produce and validate technical design","depends_on":[1]},{"step":3,"action":"Prepare dependency report","purpose":"Produce and validate dependency report",... | [{"step":1,"action":"Prepare delivery plan","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare technical design","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":... | [{"item":"delivery_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"technical_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_report","check":"Check structure, completeness and consistency.","result":"sim... | {"status":"success","completed_outputs":["delivery_plan","technical_design","dependency_report","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | test_complex_delivery | test | true | 1.0.0 | ||
atm_0002071 | Coordinate a complex application delivery with technical dependencies and stakeholder communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Coordinate a complex application delivery with technical dependencies and stakeholder communication. Context: ... | ["project_management","backend_engineering","app_development","email_writing"] | expert | success | ["api_client","spreadsheet","browser","document_editor","testing_framework","database"] | ["Do not claim that an action succeeded without evidence.","Validate calculations before presenting conclusions.","Avoid exposing credentials or private information."] | ["delivery_plan","technical_design","dependency_report","email_draft"] | [{"step":1,"action":"Prepare delivery plan","purpose":"Produce and validate delivery plan","depends_on":[]},{"step":2,"action":"Prepare technical design","purpose":"Produce and validate technical design","depends_on":[1]},{"step":3,"action":"Prepare dependency report","purpose":"Produce and validate dependency report",... | [{"step":1,"action":"Prepare delivery plan","tool":"database","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare technical design","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pr... | [{"item":"delivery_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"technical_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_report","check":"Check structure, completeness and consistency.","result":"sim... | {"status":"success","completed_outputs":["delivery_plan","technical_design","dependency_report","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | test_complex_delivery | test | true | 1.0.0 | ||
atm_0002072 | Analyse financial records, calculate key indicators, produce a report and prepare a communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Analyse financial records, calculate key indicators, produce a report and prepare a communication. Context: Th... | ["document_creation","financial_analysis","email_writing","data_analysis"] | expert | success | ["terminal","browser","api_client","chart_generator","document_editor","database","python","email_client"] | ["Explain uncertainty and missing information.","Respect dependencies between tasks.","Report errors instead of silently ignoring them."] | ["validated_metrics","financial_report","executive_summary","email_draft"] | [{"step":1,"action":"Prepare validated metrics","purpose":"Produce and validate validated metrics","depends_on":[]},{"step":2,"action":"Prepare financial report","purpose":"Produce and validate financial report","depends_on":[1]},{"step":3,"action":"Prepare executive summary","purpose":"Produce and validate executive s... | [{"step":1,"action":"Prepare validated metrics","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare financial report","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"act... | [{"item":"validated_metrics","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"financial_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"executive_summary","check":"Check structure, completeness and consistency.","result":... | {"status":"success","completed_outputs":["validated_metrics","financial_report","executive_summary","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | financial_reporting | train | true | 1.0.0 | ||
atm_0002073 | Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. Context: The task ... | ["software_testing","terminal_operations","project_management","debugging"] | advanced | impossible | ["terminal","browser","chart_generator","code_editor","file_manager","testing_framework","document_editor"] | ["Report errors instead of silently ignoring them.","Avoid exposing credentials or private information.","Respect dependencies between tasks.","Do not claim that an action succeeded without evidence."] | ["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"] | [{"step":1,"action":"Prepare incident summary","purpose":"Produce and validate incident summary","depends_on":[]},{"step":2,"action":"Prepare root cause hypothesis","purpose":"Produce and validate root cause hypothesis","depends_on":[1]},{"step":3,"action":"Prepare recovery plan","purpose":"Produce and validate recover... | [{"step":1,"action":"Prepare incident summary","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare root cause hypothesis","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"ac... | [{"item":"incident_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"root_cause_hypothesis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"recovery_plan","check":"Check structure, completeness and consistency.","result":... | {"status":"impossible","completed_outputs":[],"reason":"The requested outputs contradict a stated constraint.","message":"Explain the limitation and identify a feasible alternative."} | test_recovery_workflow | test | true | 1.0.0 | ||
atm_0002074 | Transform a dataset into a dashboard with clear visualizations and a supporting data service. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Transform a dataset into a dashboard with clear visualizations and a supporting data service. Context: The ava... | ["backend_engineering","data_analysis","ui_ux_design","app_development","cross_domain_execution","terminal_operations","financial_analysis"] | advanced | impossible | ["browser","document_editor","chart_generator","code_editor","database"] | ["Avoid exposing credentials or private information.","Use accessible and understandable interfaces.","Respect dependencies between tasks.","Keep outputs structured and easy to inspect.","Explain uncertainty and missing information."] | ["data_quality_report","dashboard_spec","backend_design","verification_plan"] | [{"step":1,"action":"Prepare data quality report","purpose":"Produce and validate data quality report","depends_on":[]},{"step":2,"action":"Prepare dashboard spec","purpose":"Produce and validate dashboard spec","depends_on":[1]},{"step":3,"action":"Prepare backend design","purpose":"Produce and validate backend design... | [] | [{"item":"data_quality_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dashboard_spec","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"si... | {"status":"impossible","completed_outputs":[],"reason":"The requested outputs contradict a stated constraint.","message":"Explain the limitation and identify a feasible alternative."} | data_dashboard | train | true | 1.0.0 | ||
atm_0002075 | Plan a database migration with validation, rollback considerations and application compatibility. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a database migration with validation, rollback considerations and application compatibility. Context: Sev... | ["software_testing","backend_engineering","terminal_operations","database_management","project_management","api_integration"] | expert | recovered | ["api_client","spreadsheet","python","email_client"] | ["Use accessible and understandable interfaces.","Validate calculations before presenting conclusions.","Keep outputs structured and easy to inspect.","Preserve original source data.","Avoid exposing credentials or private information."] | ["migration_plan","schema_changes","validation_checks","rollback_plan"] | [{"step":1,"action":"Prepare migration plan","purpose":"Produce and validate migration plan","depends_on":[]},{"step":2,"action":"Prepare schema changes","purpose":"Produce and validate schema changes","depends_on":[1]},{"step":3,"action":"Prepare validation checks","purpose":"Produce and validate validation checks","d... | [{"step":1,"action":"Prepare migration plan","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare schema changes","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":... | {"code":"test_failure","description":"A test did not meet its expected condition."} | [{"item":"migration_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"schema_changes","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"validation_checks","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"recovered","completed_outputs":["migration_plan","schema_changes","validation_checks","rollback_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Use a documented alternative when authorized.","Preserve the original data before attempting a correction... | database_migration | train | true | 1.0.0 | |
atm_0002076 | Plan a database migration with validation, rollback considerations and application compatibility. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a database migration with validation, rollback considerations and application compatibility. Context: Sev... | ["backend_engineering","terminal_operations","software_testing","database_management"] | expert | success | ["terminal","python","chart_generator","code_editor","testing_framework","email_client"] | ["Keep outputs structured and easy to inspect.","Use accessible and understandable interfaces.","Report errors instead of silently ignoring them."] | ["migration_plan","schema_changes","validation_checks","rollback_plan"] | [{"step":1,"action":"Prepare migration plan","purpose":"Produce and validate migration plan","depends_on":[]},{"step":2,"action":"Prepare schema changes","purpose":"Produce and validate schema changes","depends_on":[1]},{"step":3,"action":"Prepare validation checks","purpose":"Produce and validate validation checks","d... | [{"step":1,"action":"Prepare migration plan","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare schema changes","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare... | [{"item":"migration_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"schema_changes","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"validation_checks","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"success","completed_outputs":["migration_plan","schema_changes","validation_checks","rollback_plan"],"message":"The planned outputs are represented as completed in this synthetic example."} | database_migration | train | true | 1.0.0 | ||
atm_0002077 | Coordinate a complex application delivery with technical dependencies and stakeholder communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Coordinate a complex application delivery with technical dependencies and stakeholder communication. Context: ... | ["email_writing","project_management","backend_engineering","app_development","api_integration"] | expert | success | ["browser","email_client","file_manager","testing_framework"] | ["Report errors instead of silently ignoring them.","Keep outputs structured and easy to inspect.","Preserve original source data.","Validate calculations before presenting conclusions."] | ["delivery_plan","technical_design","dependency_report","email_draft"] | [{"step":1,"action":"Prepare delivery plan","purpose":"Produce and validate delivery plan","depends_on":[]},{"step":2,"action":"Prepare technical design","purpose":"Produce and validate technical design","depends_on":[1]},{"step":3,"action":"Prepare dependency report","purpose":"Produce and validate dependency report",... | [{"step":1,"action":"Prepare delivery plan","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare technical design","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step... | [{"item":"delivery_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"technical_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_report","check":"Check structure, completeness and consistency.","result":"sim... | {"status":"success","completed_outputs":["delivery_plan","technical_design","dependency_report","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | test_complex_delivery | test | true | 1.0.0 | ||
atm_0002078 | Design an automated workflow with dependencies, error handling and organized outputs. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an automated workflow with dependencies, error handling and organized outputs. Context: The outputs mus... | ["workflow_automation","file_management","api_integration","project_management"] | intermediate | failed | ["file_manager","terminal","chart_generator","spreadsheet","database","browser","document_editor","python"] | ["Avoid exposing credentials or private information.","Do not claim that an action succeeded without evidence.","Use accessible and understandable interfaces.","Preserve original source data."] | ["workflow_specification","dependency_map","error_policy","implementation_plan"] | [{"step":1,"action":"Prepare workflow specification","purpose":"Produce and validate workflow specification","depends_on":[]},{"step":2,"action":"Prepare dependency map","purpose":"Produce and validate dependency map","depends_on":[1]},{"step":3,"action":"Prepare error policy","purpose":"Produce and validate error poli... | [{"step":1,"action":"Prepare workflow specification","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare dependency map","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step... | {"code":"permission_denied","description":"The requested operation lacks authorization."} | [{"item":"workflow_specification","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"error_policy","check":"Check structure, completeness and consistency.","result":"s... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | business_automation | train | true | 1.0.0 | |
atm_0002079 | Analyse financial records, calculate key indicators, produce a report and prepare a communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Analyse financial records, calculate key indicators, produce a report and prepare a communication. Context: Th... | ["email_writing","data_analysis","document_creation","financial_analysis"] | advanced | clarification | ["email_client","browser","chart_generator","python","testing_framework","spreadsheet"] | ["Respect dependencies between tasks.","Explain uncertainty and missing information.","Use accessible and understandable interfaces.","Keep outputs structured and easy to inspect."] | ["validated_metrics","financial_report","executive_summary","email_draft"] | [{"step":1,"action":"Prepare validated metrics","purpose":"Produce and validate validated metrics","depends_on":[]},{"step":2,"action":"Prepare financial report","purpose":"Produce and validate financial report","depends_on":[1]},{"step":3,"action":"Prepare executive summary","purpose":"Produce and validate executive s... | [] | Which requirements are mandatory and which are optional? | [{"item":"validated_metrics","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"financial_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"executive_summary","check":"Check structure, completeness and consistency.","result":... | {"status":"needs_clarification","completed_outputs":[],"question":"Which requirements are mandatory and which are optional?","message":"Pause consequential execution until the ambiguity is resolved."} | financial_reporting | train | true | 1.0.0 | |
atm_0002080 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The workflo... | ["document_creation","research","decision_making","email_writing","data_analysis","workflow_automation","debugging"] | very_complex | success | ["api_client","database","testing_framework","email_client"] | ["Preserve original source data.","Explain uncertainty and missing information.","Keep outputs structured and easy to inspect.","Respect dependencies between tasks."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3... | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"success","completed_outputs":["research_summary","comparison","proposal","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | research_to_proposal | train | true | 1.0.0 | ||
atm_0002081 | Inspect a software project, diagnose a reported problem, propose a correction and verify it. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Inspect a software project, diagnose a reported problem, propose a correction and verify it. Context: Several ... | ["terminal_operations","software_testing","file_management","debugging"] | intermediate | recovered | ["browser","testing_framework","terminal","email_client","document_editor"] | ["Report errors instead of silently ignoring them.","Respect dependencies between tasks.","Do not claim that an action succeeded without evidence."] | ["diagnosis","repair_plan","test_results","change_summary"] | [{"step":1,"action":"Prepare diagnosis","purpose":"Produce and validate diagnosis","depends_on":[]},{"step":2,"action":"Prepare repair plan","purpose":"Produce and validate repair plan","depends_on":[1]},{"step":3,"action":"Prepare test results","purpose":"Produce and validate test results","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare diagnosis","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare repair plan","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Pr... | {"code":"permission_denied","description":"The requested operation lacks authorization."} | [{"item":"diagnosis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"repair_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"test_results","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"recovered","completed_outputs":["diagnosis","repair_plan","test_results","change_summary"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Report the remaining limitation if recovery is not possible.","Use a documented alternative when authorized."]} | terminal_debugging | train | true | 1.0.0 | |
atm_0002082 | Collect source information, create structured documents and prepare organized deliverables. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Collect source information, create structured documents and prepare organized deliverables. Context: The proje... | ["email_writing","file_management","research","document_creation"] | advanced | recovered | ["file_manager","code_editor","terminal","api_client","database"] | ["Avoid exposing credentials or private information.","Report errors instead of silently ignoring them.","Preserve original source data.","Explain uncertainty and missing information."] | ["source_notes","main_document","file_index","email_draft"] | [{"step":1,"action":"Prepare source notes","purpose":"Produce and validate source notes","depends_on":[]},{"step":2,"action":"Prepare main document","purpose":"Produce and validate main document","depends_on":[1]},{"step":3,"action":"Prepare file index","purpose":"Produce and validate file index","depends_on":[2]},{"st... | [{"step":1,"action":"Prepare source notes","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare main document","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prep... | {"code":"invalid_format","description":"An input file has an unexpected format."} | [{"item":"source_notes","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"main_document","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"file_index","check":"Check structure, completeness and consistency.","result":"simulated_chec... | {"status":"recovered","completed_outputs":["source_notes","main_document","file_index","email_draft"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Request the missing input from the user.","Report the remaining limitation if recovery is not possible.","Correct the... | document_workflow | train | true | 1.0.0 | |
atm_0002083 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The outputs... | ["decision_making","research","document_creation","email_writing","financial_analysis","debugging"] | intermediate | success | ["database","browser","api_client","code_editor","spreadsheet","file_manager","document_editor","email_client"] | ["Use accessible and understandable interfaces.","Report errors instead of silently ignoring them.","Do not claim that an action succeeded without evidence.","Avoid exposing credentials or private information.","Respect dependencies between tasks."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"P... | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"success","completed_outputs":["research_summary","comparison","proposal","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | research_to_proposal | train | true | 1.0.0 | ||
atm_0002084 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The outputs must be o... | ["software_testing","api_integration","app_development","backend_engineering"] | intermediate | clarification | ["email_client","chart_generator","file_manager","api_client","python"] | ["Use accessible and understandable interfaces.","Preserve original source data.","Keep outputs structured and easy to inspect."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Which requirements are mandatory and which are optional? | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"needs_clarification","completed_outputs":[],"question":"Which requirements are mandatory and which are optional?","message":"Pause consequential execution until the ambiguity is resolved."} | api_product | train | true | 1.0.0 | |
atm_0002085 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The availab... | ["research","decision_making","email_writing","document_creation"] | expert | impossible | ["chart_generator","terminal","testing_framework","file_manager"] | ["Report errors instead of silently ignoring them.","Explain uncertainty and missing information.","Do not claim that an action succeeded without evidence."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"impossible","completed_outputs":[],"reason":"The task requires information that has not been supplied.","message":"Explain the limitation and identify a feasible alternative."} | research_to_proposal | train | true | 1.0.0 | ||
atm_0002086 | Analyse financial records, calculate key indicators, produce a report and prepare a communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Analyse financial records, calculate key indicators, produce a report and prepare a communication. Context: Th... | ["financial_analysis","data_analysis","document_creation","email_writing"] | very_complex | success | ["api_client","code_editor","chart_generator","browser","database"] | ["Report errors instead of silently ignoring them.","Explain uncertainty and missing information.","Use accessible and understandable interfaces."] | ["validated_metrics","financial_report","executive_summary","email_draft"] | [{"step":1,"action":"Prepare validated metrics","purpose":"Produce and validate validated metrics","depends_on":[]},{"step":2,"action":"Prepare financial report","purpose":"Produce and validate financial report","depends_on":[1]},{"step":3,"action":"Prepare executive summary","purpose":"Produce and validate executive s... | [{"step":1,"action":"Prepare validated metrics","tool":"api_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare financial report","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":... | [{"item":"validated_metrics","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"financial_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"executive_summary","check":"Check structure, completeness and consistency.","result":... | {"status":"success","completed_outputs":["validated_metrics","financial_report","executive_summary","email_draft"],"message":"The planned outputs are represented as completed in this synthetic example."} | financial_reporting | train | true | 1.0.0 | ||
atm_0002087 | Design an API-backed product with clear interfaces, input validation and tests. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an API-backed product with clear interfaces, input validation and tests. Context: The project has a lim... | ["software_testing","api_integration","app_development","backend_engineering"] | very_complex | clarification | ["api_client","terminal","code_editor","email_client"] | ["Explain uncertainty and missing information.","Avoid exposing credentials or private information.","Report errors instead of silently ignoring them."] | ["api_contract","backend_design","interface_spec","test_plan"] | [{"step":1,"action":"Prepare api contract","purpose":"Produce and validate api contract","depends_on":[]},{"step":2,"action":"Prepare backend design","purpose":"Produce and validate backend design","depends_on":[1]},{"step":3,"action":"Prepare interface spec","purpose":"Produce and validate interface spec","depends_on"... | [{"step":1,"action":"Prepare api contract","tool":"email_client","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend design","tool":"code_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Can you confirm the intended recipient and tone? | [{"item":"api_contract","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"interface_spec","check":"Check structure, completeness and consistency.","result":"simulated... | {"status":"needs_clarification","completed_outputs":[],"question":"Can you confirm the intended recipient and tone?","message":"Pause consequential execution until the ambiguity is resolved."} | api_product | train | true | 1.0.0 | |
atm_0002088 | Inspect a software project, diagnose a reported problem, propose a correction and verify it. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Inspect a software project, diagnose a reported problem, propose a correction and verify it. Context: Several ... | ["software_testing","debugging","file_management","terminal_operations","backend_engineering","decision_making","workflow_automation"] | very_complex | clarification | ["file_manager","browser","spreadsheet","terminal","database","email_client","testing_framework","chart_generator"] | ["Validate calculations before presenting conclusions.","Report errors instead of silently ignoring them.","Respect dependencies between tasks.","Do not claim that an action succeeded without evidence.","Preserve original source data."] | ["diagnosis","repair_plan","test_results","change_summary"] | [{"step":1,"action":"Prepare diagnosis","purpose":"Produce and validate diagnosis","depends_on":[]},{"step":2,"action":"Prepare repair plan","purpose":"Produce and validate repair plan","depends_on":[1]},{"step":3,"action":"Prepare test results","purpose":"Produce and validate test results","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare diagnosis","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare repair plan","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepa... | Can you confirm the intended recipient and tone? | [{"item":"diagnosis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"repair_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"test_results","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"needs_clarification","completed_outputs":[],"question":"Can you confirm the intended recipient and tone?","message":"Pause consequential execution until the ambiguity is resolved."} | terminal_debugging | train | true | 1.0.0 | |
atm_0002089 | Inspect a software project, diagnose a reported problem, propose a correction and verify it. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Inspect a software project, diagnose a reported problem, propose a correction and verify it. Context: The avai... | ["debugging","software_testing","terminal_operations","file_management","research"] | advanced | success | ["api_client","file_manager","spreadsheet","code_editor","browser","python","document_editor","chart_generator"] | ["Avoid exposing credentials or private information.","Use accessible and understandable interfaces.","Do not claim that an action succeeded without evidence.","Respect dependencies between tasks."] | ["diagnosis","repair_plan","test_results","change_summary"] | [{"step":1,"action":"Prepare diagnosis","purpose":"Produce and validate diagnosis","depends_on":[]},{"step":2,"action":"Prepare repair plan","purpose":"Produce and validate repair plan","depends_on":[1]},{"step":3,"action":"Prepare test results","purpose":"Produce and validate test results","depends_on":[2]},{"step":4,... | [{"step":1,"action":"Prepare diagnosis","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare repair plan","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare tes... | [{"item":"diagnosis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"repair_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"test_results","check":"Check structure, completeness and consistency.","result":"simulated_check"}... | {"status":"success","completed_outputs":["diagnosis","repair_plan","test_results","change_summary"],"message":"The planned outputs are represented as completed in this synthetic example."} | terminal_debugging | train | true | 1.0.0 | ||
atm_0002090 | Design an automated workflow with dependencies, error handling and organized outputs. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an automated workflow with dependencies, error handling and organized outputs. Context: The project has... | ["project_management","workflow_automation","api_integration","file_management","database_management"] | very_complex | recovered | ["api_client","file_manager","python","document_editor","testing_framework","chart_generator"] | ["Keep outputs structured and easy to inspect.","Use accessible and understandable interfaces.","Report errors instead of silently ignoring them.","Explain uncertainty and missing information."] | ["workflow_specification","dependency_map","error_policy","implementation_plan"] | [{"step":1,"action":"Prepare workflow specification","purpose":"Produce and validate workflow specification","depends_on":[]},{"step":2,"action":"Prepare dependency map","purpose":"Produce and validate dependency map","depends_on":[1]},{"step":3,"action":"Prepare error policy","purpose":"Produce and validate error poli... | [{"step":1,"action":"Prepare workflow specification","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare dependency map","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"acti... | {"code":"ambiguous_requirement","description":"The requirement has multiple plausible meanings."} | [{"item":"workflow_specification","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"error_policy","check":"Check structure, completeness and consistency.","result":"s... | {"status":"recovered","completed_outputs":["workflow_specification","dependency_map","error_policy","implementation_plan"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Use a documented alternative when authorized.","Request the missing input from the user."]} | business_automation | train | true | 1.0.0 | |
atm_0002091 | Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Compare financial scenarios, identify assumptions and prepare an evidence-based decision report. Context: The ... | ["document_creation","data_analysis","decision_making","financial_analysis"] | intermediate | clarification | ["chart_generator","document_editor","file_manager","spreadsheet","browser","python","email_client"] | ["Report errors instead of silently ignoring them.","Keep outputs structured and easy to inspect.","Preserve original source data.","Avoid exposing credentials or private information.","Validate calculations before presenting conclusions."] | ["assumptions","calculations","scenario_comparison","decision_report"] | [{"step":1,"action":"Prepare assumptions","purpose":"Produce and validate assumptions","depends_on":[]},{"step":2,"action":"Prepare calculations","purpose":"Produce and validate calculations","depends_on":[1]},{"step":3,"action":"Prepare scenario comparison","purpose":"Produce and validate scenario comparison","depends... | [] | Which requirements are mandatory and which are optional? | [{"item":"assumptions","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"calculations","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"scenario_comparison","check":"Check structure, completeness and consistency.","result":"simulat... | {"status":"needs_clarification","completed_outputs":[],"question":"Which requirements are mandatory and which are optional?","message":"Pause consequential execution until the ambiguity is resolved."} | financial_decision | train | true | 1.0.0 | |
atm_0002092 | Transform a dataset into a dashboard with clear visualizations and a supporting data service. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Transform a dataset into a dashboard with clear visualizations and a supporting data service. Context: The wor... | ["ui_ux_design","backend_engineering","data_analysis","app_development","project_management","software_testing"] | intermediate | failed | ["database","chart_generator","terminal","code_editor","document_editor"] | ["Do not claim that an action succeeded without evidence.","Avoid exposing credentials or private information.","Keep outputs structured and easy to inspect.","Report errors instead of silently ignoring them.","Respect dependencies between tasks."] | ["data_quality_report","dashboard_spec","backend_design","verification_plan"] | [{"step":1,"action":"Prepare data quality report","purpose":"Produce and validate data quality report","depends_on":[]},{"step":2,"action":"Prepare dashboard spec","purpose":"Produce and validate dashboard spec","depends_on":[1]},{"step":3,"action":"Prepare backend design","purpose":"Produce and validate backend design... | [{"step":1,"action":"Prepare data quality report","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare dashboard spec","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"... | {"code":"missing_input","description":"A required input is missing."} | [{"item":"data_quality_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dashboard_spec","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_design","check":"Check structure, completeness and consistency.","result":"si... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | data_dashboard | train | true | 1.0.0 | |
atm_0002093 | Design and implement a user-friendly application with a backend, database and verification plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design and implement a user-friendly application with a backend, database and verification plan. Context: Some... | ["backend_engineering","app_development","software_testing","database_management"] | advanced | recovered | ["spreadsheet","python","browser","code_editor","testing_framework","chart_generator","email_client","document_editor"] | ["Preserve original source data.","Respect dependencies between tasks.","Report errors instead of silently ignoring them.","Do not claim that an action succeeded without evidence."] | ["application_design","backend_plan","database_schema","test_report"] | [{"step":1,"action":"Prepare application design","purpose":"Produce and validate application design","depends_on":[]},{"step":2,"action":"Prepare backend plan","purpose":"Produce and validate backend plan","depends_on":[1]},{"step":3,"action":"Prepare database schema","purpose":"Produce and validate database schema","d... | [{"step":1,"action":"Prepare application design","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare backend plan","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step"... | {"code":"permission_denied","description":"The requested operation lacks authorization."} | [{"item":"application_design","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"backend_plan","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"database_schema","check":"Check structure, completeness and consistency.","result":"simu... | {"status":"recovered","completed_outputs":["application_design","backend_plan","database_schema","test_report"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Use a documented alternative when authorized.","Preserve the original data before attempting a correction."... | fullstack_delivery | train | true | 1.0.0 | |
atm_0002094 | Research a topic, compare alternatives, prepare a structured proposal and draft an email. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Research a topic, compare alternatives, prepare a structured proposal and draft an email. Context: The task re... | ["document_creation","decision_making","email_writing","research"] | very_complex | recovered | ["database","spreadsheet","code_editor","email_client","chart_generator","browser"] | ["Use accessible and understandable interfaces.","Validate calculations before presenting conclusions.","Respect dependencies between tasks.","Preserve original source data.","Do not claim that an action succeeded without evidence."] | ["research_summary","comparison","proposal","email_draft"] | [{"step":1,"action":"Prepare research summary","purpose":"Produce and validate research summary","depends_on":[]},{"step":2,"action":"Prepare comparison","purpose":"Produce and validate comparison","depends_on":[1]},{"step":3,"action":"Prepare proposal","purpose":"Produce and validate proposal","depends_on":[2]},{"step... | [{"step":1,"action":"Prepare research summary","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare comparison","tool":"chart_generator","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"ac... | {"code":"ambiguous_requirement","description":"The requirement has multiple plausible meanings."} | [{"item":"research_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"comparison","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"proposal","check":"Check structure, completeness and consistency.","result":"simulated_check... | {"status":"recovered","completed_outputs":["research_summary","comparison","proposal","email_draft"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Correct the issue and repeat the relevant validation.","Request the missing input from the user.","Use a documented al... | research_to_proposal | train | true | 1.0.0 | |
atm_0002095 | Analyse financial records, calculate key indicators, produce a report and prepare a communication. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Analyse financial records, calculate key indicators, produce a report and prepare a communication. Context: Th... | ["email_writing","data_analysis","document_creation","financial_analysis"] | very_complex | impossible | ["database","email_client","python","terminal","file_manager","chart_generator","testing_framework"] | ["Keep outputs structured and easy to inspect.","Explain uncertainty and missing information.","Use accessible and understandable interfaces.","Report errors instead of silently ignoring them.","Avoid exposing credentials or private information."] | ["validated_metrics","financial_report","executive_summary","email_draft"] | [{"step":1,"action":"Prepare validated metrics","purpose":"Produce and validate validated metrics","depends_on":[]},{"step":2,"action":"Prepare financial report","purpose":"Produce and validate financial report","depends_on":[1]},{"step":3,"action":"Prepare executive summary","purpose":"Produce and validate executive s... | [{"step":1,"action":"Prepare validated metrics","tool":"python","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare financial report","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | [{"item":"validated_metrics","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"financial_report","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"executive_summary","check":"Check structure, completeness and consistency.","result":... | {"status":"impossible","completed_outputs":[],"reason":"The task requires information that has not been supplied.","message":"Explain the limitation and identify a feasible alternative."} | financial_reporting | train | true | 1.0.0 | ||
atm_0002096 | Plan a small software product from requirements through implementation, testing and documentation. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Plan a small software product from requirements through implementation, testing and documentation. Context: Th... | ["software_testing","project_management","document_creation","backend_engineering","app_development","debugging","terminal_operations"] | advanced | recovered | ["browser","chart_generator","terminal","database","file_manager","python"] | ["Do not claim that an action succeeded without evidence.","Use accessible and understandable interfaces.","Keep outputs structured and easy to inspect.","Report errors instead of silently ignoring them."] | ["requirements","architecture","implementation_plan","test_report","documentation"] | [{"step":1,"action":"Prepare requirements","purpose":"Produce and validate requirements","depends_on":[]},{"step":2,"action":"Prepare architecture","purpose":"Produce and validate architecture","depends_on":[1]},{"step":3,"action":"Prepare implementation plan","purpose":"Produce and validate implementation plan","depen... | [{"step":1,"action":"Prepare requirements","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare architecture","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepar... | {"code":"test_failure","description":"A test did not meet its expected condition."} | [{"item":"requirements","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"architecture","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"implementation_plan","check":"Check structure, completeness and consistency.","result":"simula... | {"status":"recovered","completed_outputs":["requirements","architecture","implementation_plan","test_report","documentation"],"message":"The simulated issue was detected and a recovery path was completed.","recovery_actions":["Use a documented alternative when authorized.","Request the missing input from the user.","Co... | integrated_product | train | true | 1.0.0 | |
atm_0002097 | Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Investigate a disrupted workflow, isolate the problem and prepare a verified recovery plan. Context: The workf... | ["software_testing","project_management","terminal_operations","debugging"] | advanced | success | ["database","spreadsheet","terminal","browser","testing_framework","document_editor"] | ["Preserve original source data.","Keep outputs structured and easy to inspect.","Explain uncertainty and missing information.","Avoid exposing credentials or private information."] | ["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"] | [{"step":1,"action":"Prepare incident summary","purpose":"Produce and validate incident summary","depends_on":[]},{"step":2,"action":"Prepare root cause hypothesis","purpose":"Produce and validate root cause hypothesis","depends_on":[1]},{"step":3,"action":"Prepare recovery plan","purpose":"Produce and validate recover... | [{"step":1,"action":"Prepare incident summary","tool":"terminal","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare root cause hypothesis","tool":"document_editor","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3... | [{"item":"incident_summary","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"root_cause_hypothesis","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"recovery_plan","check":"Check structure, completeness and consistency.","result":... | {"status":"success","completed_outputs":["incident_summary","root_cause_hypothesis","recovery_plan","verification_report"],"message":"The planned outputs are represented as completed in this synthetic example."} | test_recovery_workflow | test | true | 1.0.0 | ||
atm_0002098 | Design an automated workflow with dependencies, error handling and organized outputs. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Design an automated workflow with dependencies, error handling and organized outputs. Context: The available i... | ["api_integration","project_management","file_management","workflow_automation"] | expert | failed | ["python","spreadsheet","file_manager","browser"] | ["Report errors instead of silently ignoring them.","Keep outputs structured and easy to inspect.","Preserve original source data."] | ["workflow_specification","dependency_map","error_policy","implementation_plan"] | [{"step":1,"action":"Prepare workflow specification","purpose":"Produce and validate workflow specification","depends_on":[]},{"step":2,"action":"Prepare dependency map","purpose":"Produce and validate dependency map","depends_on":[1]},{"step":3,"action":"Prepare error policy","purpose":"Produce and validate error poli... | [{"step":1,"action":"Prepare workflow specification","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare dependency map","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"act... | {"code":"ambiguous_requirement","description":"The requirement has multiple plausible meanings."} | [{"item":"workflow_specification","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"dependency_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"error_policy","check":"Check structure, completeness and consistency.","result":"s... | {"status":"failed","completed_outputs":[],"message":"The task could not be completed. The failure is reported explicitly.","next_step":"Investigate the error and obtain any missing authorization or input."} | business_automation | train | true | 1.0.0 | |
atm_0002099 | Organize a project workspace, inspect its contents and design a repeatable workflow. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Organize a project workspace, inspect its contents and design a repeatable workflow. Context: The user expects... | ["file_management","workflow_automation","terminal_operations","app_development","ui_ux_design","data_analysis"] | very_complex | clarification | ["document_editor","spreadsheet","file_manager","browser","code_editor","testing_framework","chart_generator","email_client"] | ["Report errors instead of silently ignoring them.","Respect dependencies between tasks.","Avoid exposing credentials or private information.","Preserve original source data.","Keep outputs structured and easy to inspect."] | ["workspace_map","workflow","validation_checks"] | [{"step":1,"action":"Prepare workspace map","purpose":"Produce and validate workspace map","depends_on":[]},{"step":2,"action":"Prepare workflow","purpose":"Produce and validate workflow","depends_on":[1]},{"step":3,"action":"Prepare validation checks","purpose":"Produce and validate validation checks","depends_on":[2]... | [{"step":1,"action":"Prepare workspace map","tool":"testing_framework","status":"simulated","evidence":"Synthetic trace; no external action was executed."}] | Should the application be designed for desktop, mobile or both? | [{"item":"workspace_map","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"workflow","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"validation_checks","check":"Check structure, completeness and consistency.","result":"simulated_c... | {"status":"needs_clarification","completed_outputs":[],"question":"Should the application be designed for desktop, mobile or both?","message":"Pause consequential execution until the ambiguity is resolved."} | validation_operations | validation | true | 1.0.0 | |
atm_0002100 | Evaluate an application concept, identify usability issues and propose testable improvements. | [{"role":"system","content":"You are a task-execution agent. Plan carefully, respect constraints, verify outputs, report uncertainty, and never claim an unexecuted action succeeded."},{"role":"user","content":"Evaluate an application concept, identify usability issues and propose testable improvements. Context: The use... | ["software_testing","ui_ux_design","app_development"] | very_complex | success | ["spreadsheet","testing_framework","browser","file_manager"] | ["Respect dependencies between tasks.","Avoid exposing credentials or private information.","Report errors instead of silently ignoring them."] | ["ux_review","issue_list","improvements","test_plan"] | [{"step":1,"action":"Prepare ux review","purpose":"Produce and validate ux review","depends_on":[]},{"step":2,"action":"Prepare issue list","purpose":"Produce and validate issue list","depends_on":[1]},{"step":3,"action":"Prepare improvements","purpose":"Produce and validate improvements","depends_on":[2]},{"step":4,"a... | [{"step":1,"action":"Prepare ux review","tool":"browser","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":2,"action":"Prepare issue list","tool":"file_manager","status":"simulated","evidence":"Synthetic trace; no external action was executed."},{"step":3,"action":"Prepare imp... | [{"item":"ux_review","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"issue_list","check":"Check structure, completeness and consistency.","result":"simulated_check"},{"item":"improvements","check":"Check structure, completeness and consistency.","result":"simulated_check"},... | {"status":"success","completed_outputs":["ux_review","issue_list","improvements","test_plan"],"message":"The planned outputs are represented as completed in this synthetic example."} | validation_application | validation | true | 1.0.0 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.