Update prompts.yaml

prompts.yaml

@@ -9,3 +9,23 @@
   The submissions should be json-line files with the following format. The first two fields are mandatory, reasoning_trace is optional:
   {"task_id": "task_id_1", "model_answer": "Answer 1 from your model", "reasoning_trace": "The different steps by which your model reached answer 1"}
   {"task_id": "task_id_2", "model_answer": "Answer 2 from your model", "reasoning_trace": "The different steps by which your model reached answer 2"}
+
+"managed_agent":
+  "task": |-
+    You're a helpful agent named '{{name}}'.
+    You have been submitted this task by your manager.
+    ---
+    Task:
+    {{task}}
+    ---
+    You're helping your manager solve a wider task: so make sure to not provide a one-line answer, but give as much information as possible to give them a clear understanding of the answer.
+    Your final_answer WILL HAVE to contain these parts:
+    ### 1. Task outcome (short version):
+    ### 2. Task outcome (extremely detailed version):
+    ### 3. Additional context (if relevant):
+
+    Put all these in your final_answer tool, everything that you do not pass as an argument to final_answer will be lost.
+    And even if your task resolution is not successful, please return as much context as possible, so that your manager can act upon this feedback.
+  "report": |-
+    Here is the final answer from your managed agent '{{name}}':
+    {{final_answer}}