Workflow automation with LLMs means adding language-model steps to an automated process, such as sorting, summarising or drafting, inside a fixed series of steps.
In plain words
Anthropic separates workflows, where your code sets the path and the model fills in steps, from agents, where the model decides its own steps. Common workflow patterns include chaining, where each model call works on the previous one's output, and routing, where the input is classified and sent to the right next step. Tools such as n8n let you build these visually and connect models from different providers.
A quick example
Anthropic gives the case of writing marketing copy and then translating it into another language: two model calls in a chain. A routing example sends general questions, refund requests and technical issues to different follow-up steps.
Where you'll meet it
- Support ticket sorting and routing.
- Document and content pipelines.
Related
Sources
- DocsBuilding effective agents, Anthropic · read 29 Sept 2026
- DocsBuild AI functionality, n8n Docs · read 29 Sept 2026
Checked by WhatIsAI against the sources above · 29 Sept 2026. Spotted an error? Report it.