Agent Orchestration
Definition
The practice of coordinating multiple AI agents (or a single agent with multiple tools) to accomplish complex tasks that exceed what any single agent can do alone. Orchestration encompasses: task decomposition (breaking a goal into subtasks), agent selection (choosing which agent or tool handles each subtask), execution sequencing (parallel vs sequential, dependencies), state management (tracking progress across agents), error handling (retries, fallbacks, escalation), and result aggregation (combining outputs into a coherent response). Common orchestration patterns include supervisor-worker, fan-out/fan-in, pipeline, and event-driven handoff.
Builder Context
Orchestration is where most multi-agent systems break down in production. The hard problems aren't the agents themselves — they're state management, error recovery, and observability across agents. Start with the simplest pattern that works: a single supervisor agent that delegates to specialist workers via tool calls. Only move to peer-to-peer A2A when you have agents that genuinely need to negotiate or maintain long-running collaborative sessions. Key tools to evaluate: LangGraph (graph-based, good for complex flows), CrewAI (role-based, good for team simulations), and Temporal (workflow engine, good for reliability). The biggest anti-pattern is orchestrating agents that should just be tools — if an 'agent' always does the same thing with the same input, it's a function, not an agent.