Companion videos

LangGraph vs CrewAI vs direct API — companion videos

The article argues that "which agent framework should we use" is the wrong default question — the right one is whether you need a framework at all, and if so which set of constraints you want it to impose. The fastest way to make that call is to watch each framework in action long enough to feel its grain. These two long tutorials give you that, one for LangGraph and one for CrewAI; pair them with the article's direct-API discussion and the choice usually becomes obvious.

Primary pick

3:09:51

LangGraph Complete Course for Beginners – Complex AI Agents with Python

freeCodeCamp.org

A long, code-along build through LangGraph's state graphs, nodes, edges, conditional routing, checkpoints, and tool use. By the end you have enough feel for the typed-state, "every transition is explicit" model that the article's comparison to CrewAI and to direct-API code stops being abstract.

What you should get from this: You can build a LangGraph agent with typed state, conditional routing, checkpoints and tool use, and feel where the explicitness pays off.

Watch or know first: Solid Python and LLM API basics; expect to code along for three-plus hours.

AI Expert note: LangGraph's API surface changes between releases, so expect some code-along snippets to need adjusting. The graph-based mental model is the durable part; verify current syntax against the official docs as you follow along.

Open video page

Also worth watching

1:05:42

CrewAI Tutorial: Complete Crash Course for Beginners

aiwithbrandon

The same kind of build, but in CrewAI's role-goal-backstory style — agents as team members, tasks as deliverables, the framework hiding the execution loop. Watch it immediately after the LangGraph course; the contrast in how much the framework decides for you is exactly what the article is asking you to weigh.

What you should get from this: You can stand up a CrewAI crew in the role-goal-backstory style and judge how its hidden execution loop compares with explicit graphs.

Watch or know first: The same Python baseline; ideally watch it straight after the LangGraph course for the contrast.

AI Expert note: CrewAI iterates quickly and tutorial code goes stale fast. Watch it for the role-goal-backstory model and the contrast with LangGraph, then check the current CrewAI docs before copying any code.

Open video page