Back to Prompt Library
implementation
AutoGen Agent Setup & Roles
Inspect the original prompt language first, then copy or adapt it once you know how it fits your workflow.
Linked challenge: Multi-Agent Dev Team for Performance Optimization
Format
Text-first
Lines
1
Sections
1
Linked challenge
Multi-Agent Dev Team for Performance Optimization
Prompt source
Original prompt text with formatting preserved for inspection.
1 lines
1 sections
No variables
0 checklist items
Set up your AutoGen environment with three agents: 'Lead Developer' (initiates tasks, provides initial code), 'Code Reviewer' (critiques code, suggests improvements), and 'Performance Tester' (executes code, measures metrics). Assign Gemini 3 (or Gemini 2.5 Pro) as the core LLM for each. Define their initial system messages and responsibilities.
Adaptation plan
Keep the source stable, then change the prompt in a predictable order so the next run is easier to evaluate.
Keep stable
Hold the task contract and output shape stable so generated implementations remain comparable.
Tune next
Update libraries, interfaces, and environment assumptions to match the stack you actually run.
Verify after
Test failure handling, edge cases, and any code paths that depend on hidden context or secrets.