Workflow vs agent
A workflow is an LLM system whose steps follow paths fixed in code, while an agent lets the model decide its own steps and tool calls. Many products sold as agentic workflows sit somewhere between the two.
Also called: agentic workflow
By Divya Sharma · Checked Nov 15, 2026 · How we review
The words agent and workflow are used loosely, and the difference matters when you build. In a workflow, you write the control flow: call the model to classify, then call it to draft, then check the draft. In an agent, you give the model tools and a goal, and it chooses what to do next in an agent loop until it decides it is done.
Which to choose
Workflows are predictable, cheaper and easier to test, because each run takes the same path. They suit tasks you can describe step by step, such as extracting fields from an invoice and filing them. Agents suit open-ended tasks where the steps cannot be known ahead of time, such as fixing a bug in an unfamiliar codebase, and they cost more in tokens, time and the risk of going off track. Anthropic's advice is to start with the simplest design that works, which is often a single model call or a short workflow, and add autonomy only when it pays off.
Agentic workflow
"Agentic workflow" usually means a workflow with some agent-like steps: a fixed outline in which one or two nodes let the model choose tools or loop. Visual tools such as n8n and code frameworks such as LangGraph let you mix fixed edges with model-driven ones. See workflow automation for the no-code side and AI agent for the fully autonomous side.
Related terms
- AI agent
- An AI agent is a system in which a language model decides its own next steps: it calls tools, reads the results and repeats until the task is done, instead of following a fixed script.
- Workflow automation (AI)
- AI workflow automation is the use of tools such as Zapier, Make or n8n to chain triggers, app actions and model calls into a process that runs on its own, like summarising each new support ticket.
- Agent loop
- An agent loop is the repeating cycle at the heart of an AI agent: the model asks for a tool call, the application runs it and returns the result, and the model decides what to do next.
- Agent orchestration
- Agent orchestration is the control of which agents or model calls run in an application, in what order, and how each next step is chosen, either by a model making the decision or by fixed code.
- Agentic AI
- Agentic AI describes software in which a language model has some control over how a task gets done: it plans steps, picks tools and acts on the results, with more autonomy than a single prompt and reply.