This week I had the opportunity to speak at the AI Builders Amsterdam event, where I shared a bit about my background, what we’re doing with Datalumina, and how we solve the challenge of standardizing event-driven generative AI applications for our clients. I recorded the talk and made it available privately on YouTube. If you’re curious about how we build and deploy fully custom generative AI applications quickly, make sure to give it a watch. You can watch the video here Let me know if you have any questions or thoughts after watching! Cheers, Dave

Hi Everybody, I'm exploring what projects I can offer with LLMs as a freelancer. What other jobs have demand that need LLMs except appointment and lead and RAG chatbots on WhatsApp etc..?

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!

I have been freelancing in AI solo without much planning, thinking about launching an AI Automation Agency specialised in Azure. Would it be a good idea to focus on building custom solutions using Azure's services (AI Studio, AI Search,...) This way I can leverage my technical background instead of competing against agencies who build using drag and drop tools. Reason: many 50-200 employee companies are looking for Azure AI specialists.

Switching between different LLM providers like OpenAI, Anthropic, or even open-source models can be cumbersome. But with just 40 lines of Python, you can now simplify this process. In this week’s video, I walk you through a factory pattern that not only unifies your interface for different models but also uses the Instructor library to give you structured outputs, making your generative AI apps more robust. Curious how this works? Check out the video to see how you can implement this in your projects and streamline your workflow. As always, I'll share the code and break it down with a simple example.