Back to challenges
Challenge

Multi-Agent Dev Team for Performance Optimization

This challenge involves building an multi-agent system. The goal is to simulate a collaborative development team focused on optimizing Python code for performance. A 'Lead Developer' agent, 'Code Reviewer' agent, and 'Performance Tester' agent, all powered by Gemini 3, will collaborate through A2A communication. They will generate, refactor, and benchmark code, using adaptive thinking budgets to manage complexity in optimization tasks and graph-based workflows for task delegation and feedback loops.

Special Purpose AgentsHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

This challenge involves building an multi-agent system. The goal is to simulate a collaborative development team focused on optimizing Python code for performance. A 'Lead Developer' agent, 'Code Reviewer' agent, and 'Performance Tester' agent, all powered by Gemini 3, will collaborate through A2A communication. They will generate, refactor, and benchmark code, using adaptive thinking budgets to manage complexity in optimization tasks and graph-based workflows for task delegation and feedback loops.

Datasets

Shared data for this challenge

Review public datasets and any private uploads tied to your build.

Loading datasets...
Learning goals

What you should walk away with

  • Master AutoGen for setting up multi-agent conversations, group chats, and task orchestration.

  • Configure multiple agents (e.g., 'Lead Developer', 'Code Reviewer', 'Performance Tester') with distinct roles and Gemini 3 as their underlying LLM.

  • Implement robust A2A communication protocols within AutoGen, enabling agents to provide feedback, request changes, and validate solutions iteratively.

  • Develop code generation capabilities for the 'Lead Developer' agent, focusing on Python functions that can be optimized.

  • Design the 'Performance Tester' agent to execute generated code, benchmark its performance (e.g., execution time, memory usage), and report metrics.

  • Integrate adaptive thinking budgets into the agents' decision-making process, allowing them to spend more 'thought tokens' on complex refactoring problems and less on straightforward code generation.

  • Create a graph-based workflow within AutoGen to manage the code optimization lifecycle, including initial generation, review, testing, refactoring, and re-testing until performance targets are met.

Start from your terminal
$npx -y @versalist/cli start multi-agent-dev-team-for-performance-optimization

[ok] Wrote CHALLENGE.md

[ok] Wrote .versalist.json

[ok] Wrote eval/examples.json

Requires VERSALIST_API_KEY. Works with any MCP-aware editor.

Docs
Manage API keys
Host and timing
Vera

AI Research & Mentorship

Starts Available now
Evergreen challenge
Your progress

Participation status

You haven't started this challenge yet

Timeline and host

Operating window

Key dates and the organization behind this challenge.

Start date
Available now
Run mode
Evergreen challenge
Explore

Find another challenge

Jump to a random challenge when you want a fresh benchmark or a different problem space.

Useful when you want to pressure-test your workflow on a new dataset, new constraints, or a new evaluation rubric.

Tool Space Recipe

Draft
Evaluation

Frequently Asked Questions about Multi-Agent Dev Team for Performance Optimization