We've Been Building AI Agents WRONG Until Now

The whole idea of creating AI Agents is so new that frameworks (like LangChain, Phidata, CrewAI, Swarm, etc.) and especially no code agent builders aren't actually good enough for mature and production ready AI agents without a LOT of additional work.

But with Pydantic AI, we're seeing that change in incredible ways. Pydantic AI implements a ton of SUPER important and often overlooked features for an agent framework - context management (for things like API keys and database sessions), logging/monitoring, testing/evaluation capabilities, error handling, and LLM output validation, just to name a few. And it's open source and free to use!

Pydantic AI is incredible but in many ways isn't actually the focus of this video. Who knows if something better is going to be released next month! The important thing to focus on here is how Pydantic AI implements a lot of these "production grade" AI agent features that any framework going forward should implement, and you should understand how to leverage.

In this video I demonstrate the power of Pydantic AI by creating a web search agent (running locally with Ollama!) from scratch using the Brave browser API. Super useful agent you could take and extend in a million ways! Instructions to run this yourself are in the link below to GitHub.

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

All the Pydantic AI agent code I cover in the video and instructions to run it yourself can be found here:

Pydantic AI:

I'm building something BIG behind the scenes, launching soon!

Come join the oTTomator Think Tank - home of the oTToDev community!

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

00:00 - What Separates Pydantic AI?
01:33 - Pydantic AI Overview
03:14 - Key Features for Production Grade Agents
06:47 - Building an Agent with Pydantic AI
14:25 - Agent Demo (Running Locally)
15:36 - Advanced Agent with Streamlit UI
17:48 - Advanced Agent Demo
19:06 - Outro

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

Join me as I push the limits of what is possible with AI. I'll be uploading videos at least two times a week - Sundays and Wednesdays at 7:00 PM CDT! Sundays and Wednesdays are for everything AI, focusing on providing insane and practical educational value. I will also post sometimes on Fridays at 7:00 PM CDT - specifically for platform showcases - sometimes sponsored, always creative in approach!

[ColeMedin]

I'm building something BIG behind the scenes, launching soon!


Come join the oTTomator Think Tank - home of the oTToDev community!

[streamerfenwick]

My god man you are a full time job just to keep up ... keep going .. love the material and the examples.

[IdPreferNot]

Really excited about PydanticAI. Having built some swarm agents for a personal asssitatnt, this library adds all the missing pieces and make for a complete but simple framework without all the not-needed abstraction like crewai, autogen, langchain etc. Please continue with more videos on this library. :)

[andydataguy]

You have a great way of explaining subjects! Glad to see your enthusiasm for pydanticAI 😁

[RamonWilliamsJr]

Really happy to know I almost understand what you’re talking about. I’m almost there

[FernandoFaraco]

Wow, nice explanation about Pydantic AI and production ready agents. You have a talent to put this things. Thank You!

[Sulayman.]

Alhamdulila!
This is awesome Cole! I have been thinking of building an app which integrates weather.

[Max_Jean]

Amazing, thanks for the deep dive! nice to see internals of how this differs from the other frameworks

[intelligentcontentacademy]

Thanks for this. I was wondering which framework to tackle and learn and this video convinced me to go with Pydantic AI

[AppliedAIAutomation]

PydanticAI is awesome. Simple. Langchain etc are over complicated. Already built some useful things with this. Great video btw.

[gregorykennedy-mindfuldude]

Awesome sauce! Great video. Looking forward to testing this

[JulianHarris]

I like the 3 word description of what an agent is: “pipes, memory, tools”. I can’t see any support for multiple agent flows. I assume the answer is “you wire them together with python” like with the atomic agents framework…?

[kenneththompson]

Awesome bro, exactly what I’m looking for! Thx

[fullofskill]

Are you working fulltime on your projects? Amazing dude anyway ❤

[dwaynecrichlow]

Appreciate the video. Awesome knowledge. Can you please make sure the IDE is clear? It's hard to make out what you're actually doing.

[nunomcarvalho]

great content !! glad I found your channel

[danielclark]

Great dome let’s do more agent use cases with pedantic and extend its api integration capabilities

[PyJu]

Are you going to be building more agents in the future? Also can this work with your n8n, flowise and openwebui config. Local ai packaged? Or are they two totally different things? Do I sack off the n8n stuff now then?

[Xeneon]

Thanks, Cole. Do you have any tips on creating an AI agency for a full-length book generation/publishing agency? Including tying in short-form marketing to promote the product?

[MatheusTassoo]

Aweasome video! which one do you recommend learn first? pydantic ai or langchain