Back to Vault
Coding Agents
Tier 4
AutoGen
Summary
Microsoft's multi-agent framework built on conversational agents: agents (and humans) converse to solve tasks, with group chats, tool use, and code execution woven into the conversation model.
Key Takeaways
- Conversation as the coordination substrate between agents
- Human-in-the-loop is a first-class participant, not an afterthought
Reliability Note
Official Microsoft repository.
Flows informed by this source
1Agent Architecture
Single-Agent vs Multi-Agent: Decide and Design
A decision flow for the most expensive architecture choice in agent systems - grounded in what actually ships versus what demos well.
01Analyze the workload for separability
02Score the three architectures
03Sketch the chosen architecture
+1 more steps to Done
Best forbuilders who have shipped a basic app before
4 steps45-75 minutesIntermediate