Datasets:

CJJones
/

ServiceNow_Search_NLP_2_JSON_LLM_Training_Sample

---
license: cc-by-sa-4.0
language:
- en
pretty_name: ServiceNow Incident Search Conversations
size_categories:
- n<1K
task_categories:
- question-answering

tags:
- llm
- tool-calling
- function-calling
- servicenow
- it-service-management
- itsm
- enterprise-ai
- support-automation
- incident-management
- structured-output
- api-generation
- ai-assistant
- enterprise-automation
- rag-compatible
- synthetic-data
- prompt-engineering
- dataset-generation
- conversational-ai
- devops
- helpdesk
annotations_creators:
- machine-generated
language_creators:
- machine-generated
multilinguality:
- monolingual
source_datasets:
- synthetic
domain:
- enterprise
- information-technology
- customer-support
- devops
task_domain:
- enterprise-ai
- workflow-automation
author:
- C. J. Jones
dataset_type:
- conversational
- structured-query
version: 1.0.0
---
This dataset contains structured User → Bot conversations demonstrating how a natural language request can be translated into a structured ServiceNow incident search API call.

The full CJ Jones' synthetic dataset catalog is available at: 
<a href="https://datadeveloper1.gumroad.com?utm_source=website&utm_medium=button&utm_campaign=cj_jones_catalog_GP" target="_blank">https://datadeveloper1.gumroad.com</a>


Each record consists of a user requesting incident data from an IT service management system and a bot responding with a JSON query specification compatible with the ServiceNow Table API.

The dataset is designed for training and evaluating LLM tool-use capabilities, specifically:

Natural language → API query translation

Incident ticket search automation

IT service desk assistant systems

Enterprise workflow copilots

Retrieval query generation

The bot responses strictly follow a structured schema that represents a ServiceNow incident table search operation.

This dataset preview includes 10 example conversation pairs.

Supported Tasks

tool-use

function calling

information extraction

enterprise automation

natural language query translation

retrieval query generation

Languages

English

Dataset Structure

Each sample contains two fields:

{
  "user": string,
  "bot": string
}
Field Descriptions
Field	Description
user	Natural language request asking for incident or ticket history
bot	Structured JSON tool call specifying the ServiceNow search parameters
Example
User: Could you get trouble tickets that mention API integration failures regarding Seattle office staff ranking 2 for post-mortem review.

Bot:
{
  "action": "servicenow.table.search",
  "parameters": {
    "tableName": "incident",
    "query": {
      "short_description": "CONTAINS: API integration failures",
      "location": "Seattle office",
      "priority": "2"
    },
    "sysparm_limit": "21",
    "sysparm_fields": "number,short_description,description,priority,sys_created_on,assignment_group,location,state",
    "sysparm_display_value": "false"
  }
}
Data Instances

Example dataset record:

{
  "user": "Locate employee reports about wireless access point outages in Marketing group for Sao Paulo office region Critical priority incidents for compliance purposes.",
  "bot": "{ \"action\": \"servicenow.table.search\", \"parameters\": { \"tableName\": \"incident\", \"query\": { \"description\": \"CONTAINS: wireless access point outages\", \"assignment_group\": \"Marketing\", \"location\": \"Sao Paulo office\", \"priority\": \"1\" }, \"sysparm_limit\": \"39\", \"sysparm_fields\": \"number,short_description,description,priority,sys_created_on,assignment_group,location,state\", \"sysparm_display_value\": \"true\" }}"
}
Dataset Creation
Source

The conversations were synthetically generated using programmatic generation techniques designed to simulate realistic enterprise IT service desk queries.

Generation introduces variation across:

issue categories

office locations

organizational departments

priority levels

request phrasing

reporting contexts

Example issue types include:

API integration failures

wireless access point outages

network switch port errors

single sign-on errors

firewall configuration errors

power supply failures

password reset requests

email delivery issues

Generation Strategy

Records were generated to maximize variation in:

user intent phrasing

department references

location mentions

priority terminology

reporting context

The output schema enforces consistent structure compatible with ServiceNow incident table queries.

Intended Use

This dataset is intended for:

training LLM agents that interact with enterprise systems

benchmarking tool-calling accuracy

developing AI service desk assistants

research on structured query generation

👤 Creator
C.J. Jones
AI engineer and developer of domain-specific synthetic datasets for reasoning and diagnostic training in LLMs.


Disclaimer: There are no implied guarrantees and user must accept all risk and resposibilities regarding the use of this and any other datasets provided by CJ Jones.

## If you liked this, you may also be interested in:

- [30k Records LLM Training Data: Linux Automation_1](https://datadeveloper1.gumroad.com/l/zfdnjn) 
- [30k Linux File Operations LLM Training](https://datadeveloper1.gumroad.com/l/xnuugm) 
- [News Search LLM Training Data](https://datadeveloper1.gumroad.com/l/faivv) 
- [RPG Combat Scenario LLM Training Data – Magician, 30,000 records](https://datadeveloper1.gumroad.com/l/lmfhbg) 
- [AI Startup Bundle](https://datadeveloper1.gumroad.com/l/dxxja) 
- [20k LLM Synthetic PenTest Reports Training Dataset](https://datadeveloper1.gumroad.com/l/lkvoo) 
- [Synthetic LLM Physics Training Dataset](https://datadeveloper1.gumroad.com/l/vghhq) 
- [100k Synthetic RPG Scenes LLM Training Dataset](https://datadeveloper1.gumroad.com/l/drbhyu) 
- [100k Contextual Microcontroller Synthetic LLM Training Dialog Dataset](https://datadeveloper1.gumroad.com/l/xscay) 
- [LLM Training Dataset 100k Antenna Design Examples](https://datadeveloper1.gumroad.com/l/sdwom) 
- [100k Synthetic LLM Multiturn Formatted Tech Support](https://datadeveloper1.gumroad.com/l/tgnvjf)
- [LLM Training Dataset 100k Drone Telemetry and Control Reasoning](https://datadeveloper1.gumroad.com/l/kzzdeb)
- [100k Specialized Vehicle Diagnostics LLM Training Dataset](https://datadeveloper1.gumroad.com/l/oizcli) 
- [LLM Training Dataset 100k Elementary Animal Comparisons QA](https://datadeveloper1.gumroad.com/l/tzvwk) 
- [LLM Training Dataset 100k Elementary Math Word Problems](https://datadeveloper1.gumroad.com/l/woypqt)
- [100k Medical Coding Synthetic LLM Training Examples](https://datadeveloper1.gumroad.com/l/rqjkwv)
- [10,000 Synthetic Power BI Automation Conversations](https://datadeveloper1.gumroad.com/l/cazjd)
- [90k+ Quickbooks LLM Training Data (Not affiliated with Quickbooks)](https://datadeveloper1.gumroad.com/l/mvzpx)