Handoffs and Routines — Stateless Orchestration
OpenAI's Swarm (October 2024) distilled multi-agent orchestration to two primitives: **routines** (instructions + tools as a system prompt) and **handoffs** (a tool that returns another Agent). No state machine, no branching DSL — the LLM routes by calling the right handoff tool. The OpenAI Agents SDK (March 2025) is the production successor. Swarm itself remains the cleanest conceptual reference — its entire source fits in a few hundred lines. The pattern is viral because the API surface is roughly "agent = prompt + tools; handoff = function returning agent." Limitation: stateless, so memory is the caller's problem.
This lesson isn’t interactive yet.
It is part of the curriculum and will get the same treatment as Phase 1 — a visual cover, hands-on labs, derivations with numeric checks and a quiz. Until then, the original lesson is the best place to read it:
Part of Phase 16 — Multi-Agent & Swarms. Use the previous / next cards below to keep browsing the phase.