Langflow is a free, open-source (MIT) drag-and-drop canvas for building AI agents and RAG apps — a visual front end over Python and LangChain that runs on your own laptop or server. In this course you start from a one-click template, learn to read and wire the canvas, build a chatbot that answers from your own documents, swap in any model you like, debug it in the live Playground, then export the finished flow as a REST API or an MCP server. You bring your own model API key; everything else is free to run.
Build your first agent flow
Work like a pro
A Langflow agent reads incoming request text, classifies it, extracts the key fields, and routes a structured summary to the right inbox — exported as an API the rest of your stack calls.
Messy free-text requests arrive pre-sorted and structured, with no manual triage.
New Flow → Agent + a "classify/extract" prompt → export as API → POST a sample request to it.
A Langflow agent is given a "fetch from a public API" tool and a calculator tool, so it can answer "Pull the latest sequence record for accession X and tell me its length" by choosing the right tool live.
A reusable bench assistant the whole group can query — exported as an API endpoint.
New Flow → Simple Agent template → add an API Request tool component → open the Playground and ask a data question.