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​

Everyone’s talking about AI agents. But the truth? Most demos you see online are just that—demos. Even big players like Apple and Amazon struggle to make their AI features work in the real world due to issues like hallucinations and unreliable outputs. In this week’s video, I break down the differences between simple workflows and true AI agents and share practical strategies for building reliable AI systems, including: - How to use workflow patterns like prompt chaining and routing to solve real problems effectively - Why agent frameworks might not be the solution you think they are - The #1 thing you need to scale AI systems successfully (hint: it’s not a new tool) Learn how to move beyond the hype and build AI systems that actually work.

If you’re a developer, you’ve probably seen Cursor IDE making waves recently. It’s been everywhere, and after five years with VS Code, I made the switch — for now. Cursor is a fork of VS Code but adds powerful AI features like autocomplete, inline edits, and a composer. If you’re familiar with VS Code, the transition is seamless. So you can still use all your settings, themes, extensions, and most importantly, the interactive window! In this week’s video, I dive into these AI features, show how they can improve your coding workflow, and help you decide if Cursor is right for you. Talk soon, Dave P.S. We’ve temporarily closed enrollment for Data Freelancer as we’ve hit our capacity. But don’t worry — some exciting updates are coming soon. We're working on some big things behind the scenes for both Datalumina as a company and the Data Freelancer program. Stay tuned for more details!

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!