A workflow in n8n is a graph of nodes: a trigger (a webhook, a schedule, a new email) starts it, and each node transforms or routes the data — calling an API, running code, asking a language model, writing a row. It occupies the space between Zapier-style no-code tools and writing the integration from scratch: visual enough to inspect, code-capable where the job needs it.
The property that decides most real deployments is where it runs. Self-hosted on the client's own server, customer data never leaves the client's infrastructure — which is why n8n shows up so often in projects where the data being automated is the sensitive part. Credentials, retries and error alerting live inside the workflow rather than in an employee's memory.
Related terms
AI agent
A language model given tools it can call and a goal to pursue, so it decides the steps rather than following a fixed script.
Tool calling
The mechanism by which a model asks the surrounding application to run a named function, and gets the result back as text.
MCP (Model Context Protocol)
An open protocol for exposing tools and data to a model, so one integration works with any client that speaks it.
The bench this belongs to
AI automationThe repetitive half of your week, handed to software that does not get bored. Inbox triage, follow-ups, reporting, data entry between tools that were never meant to talk.
