Back to Prompt Library
planning

Design a Multi-Agent Chat for Complex Request Handling

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

Linked challenge: Build Proactive Personalized Assistant with AutoGen & Gemini 2.5 Pro

Format
Text-first
Lines
1
Sections
1
Linked challenge
Build Proactive Personalized Assistant with AutoGen & Gemini 2.5 Pro

Prompt source

Original prompt text with formatting preserved for inspection.

1 lines
1 sections
No variables
0 checklist items
Expand the AutoGen setup to handle a complex, multi-step user request (e.g., 'Find me a vegetarian recipe for dinner tonight, considering I prefer low-carb options, and then add the ingredients to my shopping list.'). Design the agent roles (e.g., `RecipeFinder`, `ShoppingListManager`) and their communication flow within a `GroupChat` and `GroupChatManager` to fulfill this request. Show how these agents would dynamically use tools (even if simulated).

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.