Orchestration
The coordination layer that decides what to do next in an AI workflow — which agent runs, which tool gets called, in what order, and how outputs from one step feed into the next. Think of it like a project manager for AI tasks: it doesn't do the work itself, but makes sure the right work happens in the right sequence. When AI pipelines fail, it's often the orchestration logic that needs fixing.
In practice
You have an AI workflow: Claude searches for information, then summarizes it, then formats it into a report, then emails it. Orchestration is the code (or tool) that manages that sequence — passing outputs between steps, handling errors, deciding what runs in what order. Without it, you just have independent pieces that don't connect.
Related concepts