Agents & tools · Glossary term
What is Orchestration?
The control logic that sequences, branches, delegates, retries, pauses, resumes, and terminates work across model and tool steps.
Why does Orchestration matter?
Reliable agent behavior depends on explicit workflow decisions outside the model, especially when tasks have dependencies or consequential side effects.
Orchestration in practice
Encode stable steps as a workflow or state machine, expose bounded decisions to the model, and persist transitions before external writes.
What is the common confusion about Orchestration?
Orchestration is not synonymous with autonomy or multi-agent systems; one agent can be orchestrated through a deterministic workflow.
Learn Orchestration in the course
Lessons that name Orchestration in a title or section
- Agent Framework Tradeoffs — Graph, Role, and Actor Orchestration
Every framework sells the same demo (research agent builds a report) and hides the same bug (state schema fights with the orchestration layer).
- Stateful Graph Orchestration — Durable Execution and Checkpoints
Agent is a state machine; nodes are functions; edges are transitions; state is checkpointed after each node. Resume from any failure at the last successful checkpoint.
- Orchestration Patterns: Supervisor, Swarm, Hierarchical
Four orchestration patterns recur across 2026 frameworks: supervisor-worker, swarm / peer-to-peer, hierarchical, debate.
- 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).
- Skill Invocation and Routing
Invocation is an authority decision followed by a relevance decision. A good description helps the model choose; a good policy decides whether that choice is allowed.
Covered in Phase 11: LLM Engineering, Phase 13: Tools & Protocols, Phase 14: Agent Engineering and Phase 16: Multi-Agent & Swarms.
Related terms
- Agent HarnessThe runtime around a model that assembles context, exposes tools, manages state, enforces limits, records traces, and decides when the…
- PlanningConstructing, selecting, or revising a sequence of actions and dependencies intended to move from the current state to a goal.
- DelegationAssigning a bounded subtask to another person or agent together with the needed context, authority, output contract, and return conditions.
- Durable ExecutionRunning a workflow so its state and completed steps survive process crashes, restarts, or long waits without redoing confirmed side effects.
Sources
More terms in Agents & tools
- Agent
- Agent Harness
- Agent Memory
- Agent State
- Agent Skill
- Approval Gate
- Checkpoint
- Compensating Action
- Delegation
- Durable Execution
- Function Calling
- Human-in-the-Loop (HITL)
- MCP (Model Context Protocol)
- Multi Round-Trip Request (MRTR)
- Planning
- ReAct
- Sandbox
- Skill Bundle
- Skill Catalog
- Skill Discovery
- Skill Invocation
- Stateless MCP
- Structured Output
- Swarm
- Termination Condition
- Tool Contract
This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.