Back to Prompt Library
planning
Define CrewAI Agent Team
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Automated Generative AI Model Evaluation
Format
Text-first
Lines
1
Sections
1
Linked challenge
Automated Generative AI Model Evaluation
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Design a `CrewAI` team for generative AI model evaluation. Define at least three distinct agent roles (e.g., 'Creative Assessor', 'Technical Reviewer', 'Bias Detector'). Assign `Claude Opus 4.1` as the primary LLM for the 'Creative Assessor' and 'Technical Reviewer'. Detail their responsibilities, goals, and communication flow.
Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Preserve the role framing, objective, and reporting structure so comparison runs stay coherent.
Tune next
Swap in your own domain constraints, anomaly thresholds, and examples before you branch variants.
Verify after
Check whether the prompt asks for the right evidence, confidence signal, and escalation path.