Vendredi matin, 9 h 15. Françoise est dans son cockpit — trois écrans, à gauche l'Excel-pointeuse qu'elle tient à jour depuis quinze ans, à droite Sage, et au milieu Rembrandt depuis trois semaines. Sa tasse à la main, celle avec sa tête imprimée dessus que quelqu'un lui a offerte à Noël. Elle pivote sur sa chaise et me lance depuis son bureau : « Michel, combien on a d'inscrits pour la rentrée, d
« Hold on, we need to talk, this doesn't add up » Friday morning, 9:15 AM. Françoise is in her cockpit — three screens: on the left the Excel attendance sheet she's kept up to date for fifteen years, on the right Sage, and in the middle Rembrandt for three weeks now. Cup in hand, the one with her face printed on it that someone gave her at Christmas. She swivels in her chair and calls over from
Building a Translation Pipeline for International Contract Bidding If your company bids on international contracts, you've probably dealt with the translation bottleneck. Technical proposals need precise translation, certified documents have strict formatting requirements, and procurement deadlines don't wait for anyone. After seeing how UK public procurement translation requirements can make or
As an SDET or Automation Engineer, failing tests are part of the daily grind. With the rise of Agentic AI, fixing scripts is easier than ever—but there’s a catch that tutorials rarely mention: Scale. In a real-world enterprise suite, you aren’t dealing with 10 tests; you’re dealing with 500. When 200 of them fail right before a major release—often due to a single upstream change by another team—fe
Practical post for engineers who've hit the wall where an AI proof-of-concept works on clean data but can't connect to the legacy systems that hold actual production data. Disclosure: I work at Ailoitte, which builds AI integration layers connecting legacy infrastructure to production AI. Sharing what the engineering actually looks like. AI models expect structured, consistently formatted data. Le
The first stage of AI work is prompting. The last stage is removing the model from most of the workflow. That sounds backwards. It is not. When a workflow is new, the LLM is useful because the work is still ambiguous. You are discovering what good looks like. You try a prompt, read the output, adjust the examples, change the tone, add constraints, and run it again. That is a good use of AI. But if
You write a detailed design doc. You paste it into your AI assistant. You wait. The output compiles. Tests pass. And yet — it's not quite what you designed. The auth middleware is in the wrong layer. The error handling pattern differs from the rest of the codebase. The field names don't match the schema. You fix it. Next task, same thing. This happens constantly, and it's not a model capability pr
Go is a compiled language — the code is converted into machine‑readable form before execution. From a beginner’s perspective, this means Go catches many errors during compilation, giving you cleaner, faster, and more predictable performance at runtime. Go is widely used for: API development CLI tools Microservices architecture Backend server. DEVOPS activity So it fits perfectly with the kind of