Remember last week's video where I talked about the difference between workflows and AI agents? Well... it kinda blew up on YouTube. 175k views in just 12 day! A lot of you were asking about how to implement these AI workflows. So that's what we're going to cover in this week's video: building effective AI agents in pure Python — no frameworks. Which are actually not agents but workflows... but agents get more clicks these days ghehe. In this week’s video, I show you: - How to implement the core patterns you need to understand - How easy it actually is to build them from scratch - How to piece these patterns together to build applications

Staying ahead as an AI engineer means mastering the right tools. In this week’s video, I walk you through 17 Python libraries that are essential for building reliable AI systems. From Pydantic for data validation to FastAPI for backend development, these tools cover everything from setup to scalability. You’ll also learn about advanced techniques like optimizing prompts with DSPy and scaling applications with Celery. Ready to future-proof your AI career? Watch the video below!

When building AI agents, you need them to understand your data—whether it’s PDFs, websites, or internal documents. Most tools for this are closed-source, requiring API keys and external platforms. But what if you could do it all in Python with an open-source library? In this week’s video, I show you how to build a fully open-source document extraction pipeline using Docling. You’ll learn how to: - Extract, parse, and chunk documents for AI processing. - Store and retrieve data efficiently with vector databases. - Build a working chat application that can answer questions based on your documents. Watch the video here.

OpenAI just dropped a major update: the Responses API. Whenever OpenAI releases something like this, it changes the game for developers, forcing us to rethink how we build AI applications. In this week’s video, I break down exactly what this API does, what’s changing, and whether you should migrate your projects. Key updates: - It’s a superset of the Chat Completions API (meaning it does everything Chat Completions did—plus more). - New built-in tools: Web search, file search, and computer use. - Simplified API calls, but also more abstraction—which can be both good and bad. If you’re serious about staying ahead in AI development, you’ll want to watch this. Check out the full breakdown here

Hey all! It's been a while since you've heard from me! Q1 has been crazy busy for me working on all the projects going on behind the scenes at Datalumina. I've only been able to get out a few videos. But I have another one prepared for you which is now live! This is an exciting one and I couldn't simply ignore... It's about Anthropic's Model Context Protocol (MCP) When I first encountered MCP in November 2024, I was skeptical. Another framework in the already crowded AI ecosystem? Another tool to add to the ever-growing list of technologies to learn? But then something interesting happened. As I dug deeper into MCP, I realized it wasn't just another framework—it was a fundamental protocol that could standardize how AI systems interact with the world around them. The adoption rate has been nothing short of remarkable. Looking at GitHub star history, MCP is on track to overtake all other AI frameworks in the next few months. I've just released a complete crash course for Python developers that covers everything from setting up MCP servers to production deployment. Whether you're building AI agents, chatbots, or other LLM-powered applications, MCP can simplify your development process. I'd love to hear your thoughts on MCP and how you're planning to use it in your projects! Keep coding, Dave P.S. I'm excited to announce that enrollment for the next cohort of our GenAI Accelerator is now open! Starting May 25th, this 6-week program will transform you into a production-ready AI engineer with hands-on training in LLMs, RAG, and our battle-tested GenAI Launchpad framework. Spots are limited, so check it out here: ​GenAI Accelerator Details​