Back to Prompt Library
planning

Design CrewAI Agent Roles and Tasks

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

Linked challenge: Recommender Multi-Agent for Complex Suggestions

Format
Text-first
Lines
1
Sections
1
Linked challenge
Recommender Multi-Agent for Complex Suggestions

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Define the necessary agent roles (e.g., Listener Profile Analyst, Musicologist Agent, Trend Forecaster Agent) and their individual tasks within CrewAI. Detail how these agents will collaborate to process a complex recommendation request. Consider which agent will be responsible for initial parsing, RAG queries, MCP tool invocation, and final recommendation synthesis. Specify the input and output for each task and how they will be passed between agents.

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.