Skip to main content
Back to Prompt Library
implementation

Configure AutoGen Auditor Agents

Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.

Linked challenge: OSHA Plant Safety Audit Multi-Agent System with AutoGen

Format
Code-aware
Lines
11
Sections
3
Linked challenge
OSHA Plant Safety Audit Multi-Agent System with AutoGen

Prompt source

Original prompt text with formatting preserved for inspection.

11 lines
3 sections
No variables
0 checklist items
from autogen import ConversableAgent, GroupChat, GroupChatManager

auditor = ConversableAgent(
    name='OSHA_Auditor',
    system_message='Review maintenance logs against OSHA 29 CFR 1910 standards. Highlight violations.',
    llm_config={'config_list': [{'model': 'gpt-4o'}]}
)

engineer = ConversableAgent(
    name='Plant_Engineer',
    system_message='Provide equipment context and operational logs.',
    llm_config={'config_list': [{'model': 'gpt-4o'}]}
)

Adaptation plan

Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.

Keep stable

Hold the task contract and output shape stable so generated implementations remain comparable.

Tune next

Update libraries, interfaces, and environment assumptions to match the stack you actually run.

Verify after

Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.