Week 12 — Lesson 3: Tool execution and conversation history

3 min

The router of Exercise 1 kept a few named strings in its state. A NorthPeak agent that talks with a technician needs more: the whole conversation, growing at every step, plus a way to run query_database and search_manuals when the model asks for them. With MessagesState the whole conversation lives in the state, the model asks for tools as messages, and a ToolNode runs them and answers with messages. This lesson explains the message list, its reducer, the four kinds of messages, and one real run on machine M014.

Preview — the rest of the lesson is for enrolled readers.

Already enrolled with a code?

Your access is tied to your account, not to this link. Sign in with the same email you used in class: your course is waiting, no need to enter the code again.

Sign inNo account yet? Create one
This lesson is part of the “Week 12 — Stateful workflows with LangGraph” module

The first modules of the course are open to everyone. For the rest you have three options: buy this course once and for all, subscribe, or enter the code handed out in class.

Are you a student on this course?

The code is tied to your account: sign in or create an account and it will be applied automatically when you come back.

No account yet? Create one