THE BEST Tool for AI Agent Workflows - LangGraph FULL Guide

This is the 7th video in the AI Agents masterclass series!
Artificial Intelligence is no doubt the future of not just software development but the whole world. And I'm on a mission to master it - focusing first on mastering AI Agents.
In this video I give a short and sweet guide and implementation of LangGraph - an extremely powerful tool for coding custom agentic workflows. Since this is a part of the AI Agents Masterclass series, I extend the Asana task management AI agent to use LangGraph to handle all the tool calling!
All code for this LangGraph guide and implementation can be found here:
github.com/col...
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
If you are curious to learn more about LangGraph, check out the documentation here:
langchain-ai.g...
Conceptual guides to LangGraph I mentioned in the video:
langchain-ai.g...
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Join me as I push the limits of what is possible with AI. I'll be uploading videos twice a week - Sundays and Wednesdays at 7:00 PM CDT!

[@themax2go]

very well explained, thank you! (still watching)

[@ArgiSanchez]

Thank you very much for sharing this incredible knowledge with all of us, and so well explained, thanks a lot, ... wonderful work !!

[@ColeMedin]

Thank you Argi, I appreciate the kind words a ton!

[@ArgiSanchez]

your code looks great, well structured, accurate and professional, congratulations !!

[@ColeMedin]

Thank you Argi, I appreciate it a lot!!

[@yaseenal-wesabi5964]

Good work.

[@ColeMedin]

Thank you!!

[@mahoanghai3364]

great work

[@stonedizzleful]

Spaghetti is my JS framework of choice

[@themax2go]

spaghetti is yummy with the right tomato sauce and fresh succulent veggies in it 🫑🍄🥦🧄🧅...🍝

[@ArgiSanchez]

I am using miniconda for environments, what version of python do you recommend for production? 3.10, 3.11, 3.12, or ???

[@aaagaming2023]

LangGraph recommends 3.11 I believe.

[@ColeMedin]

@aaagaming2023 is correct, 3.11 is recommended! With lower version of Python, you'll have issues streaming the LLM tokens with LangGraph (their documentation claims this and I tested it myself as well!).

[@ArgiSanchez]

when a Multi-Agent exemple ? 😅 pleeeease ...

[@ColeMedin]

@@ArgiSanchez don't worry, that's coming soon! 😉

[@AbhishekSingh-pj1oo]

how will we pass the database session from node to node?

[@ColeMedin]

Great question! There are a few ways to do this, but the best way would be to leverage LangGraph's built in support for context objects (they even specifically call out DB connections!): langchain-ai.github.io/langgraph/how-tos/state-context-key/

[@AbhishekSingh-pj1oo]

@@ColeMedin The previous or prevalent way to do this delegates entire db functions and everything to tools. And maybe use ToolNode. I have to test both for performance, but this is a sqlalchemy or rest api (say fastapi) problem and is independent of LangGraph.