A Hands-On Course · 9 lessons

Multi-Agent Systems

Orchestrate multiple agents — fan-out and synthesis, coordination contracts, verify-gated completion, and the failure taxonomy.

Short lessons (~5–8 min each), each with one tangible win and a retrieval-practice quiz. Built for engineers who already use AI coding tools and want the non-obvious mechanics.

Grounded in the agentpatterns.ai corpus (CC BY 4.0). Keep the Glossary open as you go.

Part 1 · When and How

1 When Many Agents Beat One A second agent feels like more horsepower. Usually it's more coordination cost for no quality return. The first skill is knowing when not to. 2 The Orchestrator and Its Workers The canonical multi-agent shape. One agent decomposes and synthesizes; the others run bounded subtasks in parallel and never talk to each other. 3 Fan-Out and Synthesis Same problem, N agents, different starting conditions. Then one agent assembles the best parts of each — not a vote, not a summary, a deliberate merge.

Part 2 · Coordination Contracts

4 Forked vs Fresh Subagents When you spawn a child, it either inherits the parent's whole mind or starts from a clean brief. The choice trades cache savings and nuance against bias and an injection surface. 5 Handoffs and Coordination Contracts Every agent works in its own context window. The handoff between them is the one channel — and the single largest place multi-agent systems lose information. 6 Verify-Gated Completion The agent that did the work is the worst judge of whether it's done. Put a separate, read-only verifier on the critical path of every "done" claim — and make silence mean reject.

Part 3 · Operating the Fleet

7 Why Multi-Agent Systems Fail A study of 1,600+ production traces sorts the failures into three buckets — and most of them are design problems, not model problems. The prompt is the usual culprit. 8 Rainbow Deployments Agents are stateful, so you can't just flip the switch to a new version. Keep N versions running at once; new sessions take the latest, old ones drain where they started.

Capstone

9 The Multi-Agent Decision Table Eight lessons, one reflex: default to one agent, and add coordination only where the task structure forces it. Here's the whole course as a lookup table — and a mixed review to prove it stuck.