← All drillsMulti-Agent Patterns
What you'll be able to do- ✓Build an orchestrator that plans at run time, delegates to specialist workers, and guards against a step no worker can do
- ✓Build a supervisor that routes, applies a quality gate, and escalates instead of looping
- ✓Compare a flat supervisor with a two-level hierarchy on the same tickets and read the cost of the extra level
- ✓Build a sequential pipeline that validates every hop, and see why shape checks alone let a wrong answer through
- ✓Run independent checks in parallel and merge them in code, including when one branch fails
- ✓Map one worker over many chunks, reduce in code or with a tree, and test a debate and its judge against known answers
Pick how several agents should be organised before you build them, and know the failure each arrangement brings - the decision that comes before every multi-agent system.
⌁ Support-automation and research agents built with LangGraph, Google ADK, AWS Strands Agents and AutoGen, and the planner-and-workers designs inside coding agents.
Start this internshipCreate an account to unlock the 9 sections, the workbench, and askThili.
BeginSections
1. Multi-Agent Patterns: Orchestrator, Supervisor, Hierarchy, Pipeline, Fan-Out, MapReduce, Debate
🔒 locked2. Lesson 1 - Orchestrator-Subagent: plan once, delegate to specialists
🔒 locked3. Lesson 2 - Supervisor: route, watch, check, loop back
🔒 locked4. Lesson 3 - Hierarchical: supervisors of supervisors
🔒 locked5. Lesson 4 - Sequential Pipeline: fixed stages, validated at every hop
🔒 locked6. Lesson 5 - Parallel Fan-Out / Fan-In: independent checks at once
🔒 locked7. Lesson 6 - MapReduce: the same worker over many chunks, then combine
🔒 locked8. Lesson 7 - Debate: two sides argue, one judge decides
🔒 locked9. Lesson 8 - Choosing: which pattern for which job
🔒 lockedDig deeper
🔗Building Effective Agents - Anthropic Engineering
article📄AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation (Wu et al., 2023, arXiv:2308.08155)
paper📄MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework (Hong et al., 2023, arXiv:2308.00352)
paper📄Improving Factuality and Reasoning in Language Models through Multiagent Debate (Du et al., 2023, arXiv:2305.14325)
paper📄MapReduce: Simplified Data Processing on Large Clusters (Dean and Ghemawat, OSDI 2004)
paper🔗Groq - free API keys for open models
docs