Back to Prompt Library
planning
Design Agent Roles and Graph Structure
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Conversational Commerce Agent with LangGraph & Gemini 2.5 Pro
Format
Text-first
Lines
1
Sections
1
Linked challenge
Conversational Commerce Agent with LangGraph & Gemini 2.5 Pro
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Outline the key agent roles (e.g., `ProductSearcher`, `CartManager`, `PaymentProcessor`, `OrderConfirmer`) needed for the conversational commerce system. Design the LangGraph state and flow, specifying how agents pass information and control, including conditional routing for decisions like 'product found' or 'payment failed'. Consider how to manage conversational history and context persistence.
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.