An experiment in using AI code agents to write all the missing unit tests for an existing codebase. Let’s take code coverage to 100%.

Rock climbing is one of my favourite ways to blow off steam. Whenever I tell people about that hobby, I get a common response: “Sounds really cool, but I could never do that because of my fear of heights…” Fear of heights is real, and it’s something we all have. In order to climb, we need to conquer that fear. And the only way to conquer that fear is… to climb. ...

Traditional hourly billing is broken for software agencies — AI enables faster development while introducing new costs, necessitating value-based pricing.

In my line of work, I see a lot of legacy code – products that were built so fast the foundations are weak. Every little change causes something else to break. The industry standard way to stabilise such a codebase has always been test automation. But writing unit tests takes time, and in the rush of shipping features, that time is often dedicated to anything but tests. As the product expands and the code gets ever more complex, this lack of tests becomes a painful problem. If small changes break the system, sweeping changes are downright scary. The team gets paralysed. ...

LLMs are productivity multipliers for software engineers. Over the last few years, the quality of their output has reached a professional level. They cannot one-shot a complete SaaS product (yet), but it’s more than just fancy autocomplete. What used to take an hour now takes minutes. Once you get used to building with AI-powered tools, the alternative feels awkward. I remember developing software in the early 2000s. The internet existed, but treasure troves like Stack Overflow didn’t. Building something with a new framework meant buying and reading the physical book. Before hoodies were in, the sign of the real developer was a stack of O’Reilly books on your desk. ...

People, in general, don’t care about privacy. They like the idea of their data being safe, but their actions tell another story. They’ll click on any link and sign up for the shadiest free tools without giving it a second thought. If you’re not paying for a service, it means you’re the product, and people have shown over and over again that they are OK with that. AI tools take this careless behaviour to the next level. I think it’s safe to assume that ChatGPT hears more confessions than the average priest. People freely share medical information and financials with their LLM. ...

LLMs are stochastic parrots. They just predict the next most likely word. And the most likely token to follow “AI” these days is, without a doubt, “Agents”. AI agents are hailed as the next quantum leap in the evolution towards building SkyNet AGI. An agent is basically a program that can interpret input with an LLM and has access to tools to actually do something with that input. Instead of ChatGPT drafting you an email, an agent could send emails on your behalf. You could ask your agent to “send friendly reminders to fill out that Doodle”, and it could read your latest Doodle, see who didn’t reply yet and then ask the Gmail agent to send those reminders to the right people. Rather than text-in-text-out, an agent converts input into actions. ...

Earlier, I discussed how AI-generated podcasts could be a more engaging way of sharing business information. While the podcast format is great to learn new material, it’s not an ideal fit to summarize a bunch of articles. It doesn’t feel natural to have two hosts yapping about a single article as if it is a discussion. But podcasts can be a source of inspiration… One of my regular podcasts is De Zeven by Belgian newspaper De Tijd. Every morning at seven o’clock, it discusses seven news items in seven minutes. It’s a convenient way to get up to speed quickly with the events of the day. ...

Google NotebookLM is a fantastic learning tool. It allows you to link up to 300 sources and will distill all that information into a single model. Let’s say you want to have a basic understanding of the EU AI Act. It’s a long, boring document. You can add it as a source, together with a few YouTube videos on the topic. Maybe add a note describing your company. You now have a ChatGPT-style model you can ask targeted questions. ...

Despite all the promises of AI, more tokens are spent on generating inane content than on trying to cure cancer. AI is literally everywhere. At least: on the internet… As a CTO and overall technology enthusiast, I try to stay somewhat on top of the wild set of innovations that roll out daily. That means spending a lot of time online, reading about and experimenting with new tools. Yet, when talking to customers, I see a huge gap between what’s shared on socials and what happens in the workplace. ...