Back to Prompt Library
implementation

Crew Definition and Tasking

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

Linked challenge: Autonomous AI Policy Auditor using CrewAI, Mem0 and Exa

Format
Text-first
Lines
1
Sections
1
Linked challenge
Autonomous AI Policy Auditor using CrewAI, Mem0 and Exa

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Define a Research Crew with a Lead Researcher agent and a Policy Writer agent. The Researcher must use the Exa search tool. Ensure the Task description specifies that only real-world sources are permitted. Assign Claude Opus 4.6.6 as the LLM for the Writer agent.

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.