After two years of building with GenAI, here’s what I wish I’d had from day one... This has been a long time in the making, and I’m excited to finally pull back the curtain on what we’ve been building behind the scenes: The GenAI Launchpad — officially launched on Product Hunt today! 🎉 For the past two years, my team and I at Datalumina have been deeply involved in the world of AI, building solutions with large language models (LLMs) for clients across industries. Each project taught us so much about what it takes to bring AI to life in practical, high-impact ways. But there was one recurring challenge... We spent way too much time setting up project structures, handling integrations, and putting out fires in the infrastructure — leaving less time for the real AI work, the work that brings ideas to life. Not only was setup eating into our time, but we also found that the agent frameworks on the market were just too optimistic. Real-world use cases are more complex and demand reliability and precision that many frameworks simply can’t deliver. So, we got to work! 👷🏼‍♂️ And after two years of trial and error, working with every system and structure you can imagine, we built our own solution. The GenAI Launchpad is the result of our journey — a project repository that streamlines everything from initial setup to deployment, ready to handle the demands of production at scale. And the time savings? ⏳ We’ve calculated that it saves us over 50 hours per project on average, so we can dive right into the creative work that actually advances AI. Today, we’re launching the GenAI Launchpad to share that time-saving power with you — our community of fellow AI enthusiasts and builders. This is more than just a repository; it’s a battle-tested, engineer-approved blueprint that I wish I’d had when we started. It’s here to help you skip the headaches, bypass the boilerplate, and focus on what matters: building innovative AI solutions for real-world problems. If you’ve ever spent weeks fighting project setup, only to finally reach the real work, then you’ll understand why I’m so excited to share this.

After doing a bunch of projects for everything but AI Voice Agents, I finally gave into the hype. Some weeks ago, I showcased the final demo for a custom-coded AI Voice System made for one of the biggest IoT Companies in Spain, and they seemed to love it! Now I know: the ticket is not that high, specially for such a big company. But, as stated, this is the first time I dive away from RAG systems & other solutions, and go into AI Voice Agents instead. And I didn’t want to disappoint! (and no, sadly I couldn't make it a recurring subscription). Managed to get this deal thanks to a professor from a University in Spain who leads research projects in collaboration with this big IoT company, and this should be the first (and cheapest) phase of the project. We're now heading into automated document generations using OpenAI + Google Docs (for URDs, SRDs, etc.) Fully aware this is not the most impressive deal, but we're building things up slowly, there's more to come. ----------------------------------------------------------------------- Project info: 📌 What is it? Custom-built AI voice assistant that initiates interactive, outbound calls at the time desired by the user. It calls the clients from the IoT company who want to develop software projects with them and gathers all the necessary information to get started with the project and create the necessary documents (URDs, SRDs…). ⭐️ What does it solve? What they have to do without the voice agent is: fly out an employee to wherever the customer is located, and speak with them directly to gather all information they require to get started developing the software. An incredibly expensive and time-consuming task for the business. Now they can just send a form to the customer, they fill in their information + desired time for the call (instantly or at a set date and time). Then the LLM will go through a series of questions set by the company, and it will keep asking until it gathers all the necessary data from the customer.

Hi everyone, I just realized it’s been almost a month since I posted my first exercise! I was a bit hesitant to share this one, it actually took me two weeks to decide—but I thought I’d go ahead and post it anyway. This time, I'm experimenting with image segmentation, as part of a series of seven exercises I’m working on to dive into computer vision. For those who read my previous post, you might remember I’m following some ideas ChatGPT suggested for practical exercises in computer vision. I was unsure about sharing this one because I didn’t always get the outcome I expected: in some images, I managed to capture the entire edge of the leaf, while in others, I only segmented parts of it. Still, it was an interesting challenge, and I learned a lot from the process. Here’s what I focused on for this exercise: 2. Image Segmentation Objective: Explore techniques to divide an image into segments, or regions of interest. Tools: OpenCV, Scikit-Image. Exercises: - Apply thresholding techniques (binary, adaptive) - Use Otsu's method for automatic thresholding - Perform image segmentation using the Watershed algorithm - Experiment with contour detection Example Project: Segment different objects in an image (e.g., finding and counting coins) [Link to the notebook] Previous post if you did not read it: post By the way, my next exercise might take a bit longer as I am working on another project that I expect to share soon. I hope you all have a great week ahead! And please, if you have any comments on my notebook, I’d love to hear your thoughts on what I could improve or try differently.

Part 1 - So many options ... Wordpress, Django, MERN or Bubble? Hi everyone, over the last days I have mostly focused on the career and business side of things. Because knowing a lot is only one side of the coin, being able to present yourself well on Linkedin or a personal website is just as important. With this in mind I have thought to myself that it is really high time for me (especially for me as a consultant) to create a homepage, 1) to talk about the usual stuff, my skills, my service offering, testimonials, ... all the stuff you have on a run-of-the-mill freelancer website 2) to showcase some small Python poc (proof-of-concepts), some scripts I want to deploy on my website to show my skills I have not finished this project, but I like to share with you my thoughts and my progress. It has all turned out to be super complicated, but it was a learning experience and, well, I will be curious to see the chapter of Dave to see a more easy and straightforward way. So as a starting point I was confronted with four questions: 1. Should I do it myself? Definitely yes, doing it myself will allow me to learn, it will save money, and given that I have to explain things to a webdeveloper anyway I will probably not spent too much extra time (or so I thought) 2. How do I want to implement it from a technical pov? This is the focus of this text/thread 3. What is the content? I am not there yet, but I plan not to reinvent the wheel, rather find a couple of websites from "competitors" I like and present similar content. As concerns the POCs I will present whatever script I develop for myself, and that are interesting to others 4. What design? something simple ... this leads nicely back to question 2 I hope you are still with me and I am not too verboose. So concerning the technical implementation I had the following chain of thought: - The website is supposed to look good (design), so I need some CMS that allows me to re-use existing themes to quickly get to some results. Plus, I want wysiwig functionality. This basically disqualifies all the micro frameworks, like Flask, Gradio, ... while Streamlit is too simple. - So basically I am left with Wordpress, Wix, Bubble, Django, and maybe some Javascript Frameworks for static websites like Astro. As concerns Javascript based webbuilding, I do not really know about the "Gui based development environments" that exist in this context. Maybe there are some managed hosting solutions, I do not know. Maybe it is smart to have a "JS + Headless CMS solution", but all this is way too complicated for me. - Wix, Bubble and all these website builders want you to pay quite some money. So they are out. What is more, they do not have the huge ecosystem that Django and Wordpress have. - Django is a great framework, it has a Backend, admin panel, and with Mezzanine, and Wagtail you also have some CMS frameworks. So if I had more time I would go for Django and learn it inside out. - The more pragmatic solution however is Wordpress. It is also a good skill to have.

Just wanted to share the win I've been wanting to get for several months... I got a new job in the data science / ML field, where the domain matches my masters degree. I start today. If it weren't for this group and what I learned from it, I might not have made it through the interview process (4 rounds plus a take-home assignment). I also want to encourage others to keep at it, not give up, even when things seem darkest. Success may just be around the corner!