AssistantAgent, UserProxy, GroupChat, code execution sandbox.

AutoGen — Conversational Multi-Agent Framework

AutoGen (Microsoft) enables multi-agent conversations where agents collaborate by exchanging messages. AssistantAgent wraps an LLM with a system prompt and tools. UserProxyAgent executes code and relays human input. GroupChat orchestrates multiple agents in a shared conversation. The code execution sandbox (Docker or local subprocess) lets agents write and run code iteratively. AutoGen 0.4 introduced an actor-model-based runtime (AgentChat) for improved scalability.

Interactive Pipeline Flow

UnderstandImplementOptimise

📐 Define — agent configs

Define agents: AssistantAgent(name="coder", system_message="You are an expert Python developer...", llm_config={model:"gpt-4o"}). Each agent has a distinct identity and capability.

Architecture Diagrams

AutoGen iterative code generation and testing cycle.

Loading diagram...

Key Design Decisions

🐳Use Docker for code execution in production

LocalCommandLineCodeExecutor runs code on the host — a security risk. DockerCommandLineCodeExecutor isolates execution in a container with no network or filesystem access.

🛑Define clear termination conditions

Without a termination condition, GroupChat can loop indefinitely. The is_termination_msg function (checks for "TERMINATE") or max_turns parameter must be set on every agent.

💬Seed GroupChat with role clarity

Each agent in a GroupChat should have a distinct persona in its system_message. Without clear role boundaries, agents repeat each other's work or talk past each other.

Discussion