Agentic workflow (workflow vs agent)
A process where your code fixes the steps and a model does some of them, as opposed to an agent that decides its own steps.
Common shapes: prompt chaining (fixed steps with checks between them), routing (classify the input, send it to a specialized prompt or model), parallelization (independent subtasks, or the same task several times and a vote), orchestrator-workers and evaluator-optimizer (one model drafts, another critiques until it passes). A workflow is predictable, testable and cheaper; an agent handles tasks whose steps cannot be known in advance.
Related terms
- AI agent: A model that decides its next step itself, calls tools and repeats until the task is done.
- Orchestrator-workers pattern: One model plans the task, hands parts of it to worker models or subagents, and combines their results.
- Multi-agent system: Several AI agents with separate roles and contexts working on one task, usually coordinated by a lead agent or a fixed workflow.
