Fleet 1.13:Teams are now shipping 5x more PRs with autonomous pipelines.See what's new →
FleetFleet
Glossary

Agent Orchestration

Agent orchestration is the coordination layer that sequences, routes, and monitors multiple AI agents so they collaborate on a shared workflow without conflicting or duplicating effort.

A single AI agent can complete isolated tasks — write a function, summarize a document, generate a test. Orchestration addresses what happens when tasks depend on each other and different agents own different steps. The orchestrator decides which agent runs next, what context it receives, what constitutes successful completion, and what happens when something goes wrong.

Orchestration patterns range from simple sequential pipelines (A finishes, then B starts) to reactive event-driven systems (an event published by A triggers B automatically, without a central scheduler). Reactive patterns tend to be more resilient because they do not require a polling loop and naturally handle retries and partial failures.

Key orchestration concerns include: deadlock prevention when agents are waiting on each other, budget enforcement so no single agent exhausts shared token quotas, handling failures at any stage, and maintaining a tamper-evident audit trail of every decision each agent made.

How this relates to Fleet

Fleet's orchestration model is event-driven rather than pipeline-based. Agents publish structured events to a shared fabric (the event bus), and subscriptions define which agent picks up each event type. A developer agent finishing a PR publishes a pr_created event; the reviewer's subscription fires automatically. No central scheduler is required, and each step is logged to the audit trail.

Frequently asked questions

What is the difference between agent orchestration and a workflow engine?

A workflow engine typically executes a predefined DAG of steps with static routing. Agent orchestration is more dynamic: agents can publish unexpected events, subscriptions can be added or removed at runtime, and the system must handle open-ended agent outputs rather than structured return values. The boundary blurs at the edges, but agent orchestration is generally more tolerant of non-determinism.

Do you need a dedicated orchestration tool, or can agents orchestrate themselves?

Self-orchestration — agents explicitly calling each other — works for small, well-defined workflows but becomes brittle as team size grows. Coupling agents directly means changing one agent's output format breaks its downstream consumers. A dedicated orchestration layer decouples agents through a shared event schema, making individual agents easier to swap or upgrade independently.

Run your first agent fleet

One binary. Five minutes. See every agent, coordinate every handoff, and keep a full audit trail of what your fleet did.