Back to Prompt Library
planning
AutoGen Agent Design and Setup
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: AutoGen Multi-Agent Legal Tech Valuator with Gemini 3 Flash
Format
Code-aware
Lines
7
Sections
1
Linked challenge
AutoGen Multi-Agent Legal Tech Valuator with Gemini 3 Flash
Prompt source
Original prompt text with formatting preserved for inspection.
7 lines
1 sections
No variables
1 code block
Design the AutoGen agent team structure for the legal tech valuation challenge. Define at least three distinct agent roles (e.g., 'Market Analyst', 'Financial Reviewer', 'Legal Innovator'), their responsibilities, communication patterns, and how they will collaborate. Provide the Python code to initialize these agents and the GroupChat orchestrator. ```python
import autogen config_list = [ { "model": "gemini-3-flash", # Replace with your actual Gemini 3 Flash model identifier "api_key": autogen.Env.get("GEMINI_API_KEY"), "api_type": "google", # For Google models "api_base": "https://generativelanguage.googleapis.com/v1beta" }
] llm_config = { "timeout": 60, "cache_seed": 42, "config_list": config_list, "temperature": 0
} # Your agent definitions here
market_analyst = autogen.AssistantAgent( name="Market_Analyst", llm_config=llm_config, system_message="You are an expert market analyst specializing in the legal tech sector..."
) # ... (define other agents) # Your GroupChat and manager setup here
```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.