Most production AI features are not a single prompt. They retrieve data, classify inputs, call models, parse structured outputs, validate results, write records, notify users, and handle failures. That sequence is a workflow.

An AI workflow combines model calls with ordinary software steps in a controlled flow. The application decides the sequence. The model is used at specific points where it helps: classification, extraction, summarization, synthesis, ranking, or validation.

This chapter covers deterministic pipelines, DAGs, routing, map-reduce, retries, checkpointing, and a document-processing workflow. The theme is control: use the model where it helps, and keep orchestration in code when the path is known.