Blog
Technical notes & production insights.
Methodology, software architecture, AI in production: our hands-on feedback, without unnecessary jargon.
Sep 22, 2026 · AI · 10 min
Jev: the AI model that decides instead of writing
Launched in September 2026 by TypeSafe AI, Jev does not generate text: it returns typed, calibrated decisions. What it is, what it costs, and three use cases.
Read →
Sep 07, 2026 · AI · 9 min
How much does an AI project cost, from POC to production?
The model price is not the point. Where the budget actually goes, how to calculate the API versus dedicated server threshold, and what makes it slip.
Read →
Aug 28, 2026 · AI · 9 min
AI Act: what actually applies since 2 August 2026
The Digital Omnibus pushed high-risk obligations to December 2027. What already applies, what was postponed, and what to do in between.
Read →
Aug 27, 2026 · AI · 4 min
OpenRouter: one API for 417 AI models
A single gateway to hundreds of models, at the provider’s own rate and with no logging by default. What it changes, and where its limits are.
Read →
Aug 27, 2026 · AI · 8 min
Beyond SEO and SEA, Enter GEA with ChatGPT Ads
With ChatGPT Ads, advertising enters AI-generated conversations. This new lever, called GEA, may soon complement SEO, SEA, and GEO in acquisition strategies.
Read →
Aug 19, 2026 · AI · 10 min
AI coding agent: why chat alone isn’t enough to control development agents
An AI coding agent becomes more controllable when its state, decisions, drafts, and validations remain visible outside the chat.
Read →
Aug 18, 2026 · AI · 9 min
llms.txt v2: useful for AI agents, irrelevant for Google ranking
llms.txt v2 makes it easier for AI agents to access Markdown content, without improving Google ranking. Here’s what to really expect.
Read →
Aug 13, 2026 · AI · 9 min
Copilot Cowork: Microsoft Shifts from AI Assistant to Agent That Executes Work
Copilot Cowork turns Microsoft 365 Copilot into an AI agent capable of executing complex, multi-step tasks.
Read →
Aug 11, 2026 · AI · 9 min
LangChain and Security: Mistakes to Avoid with AI Agents
LangChain in business: prompt injection, sensitive data, permissions, and critical actions. Key points to secure an AI agent.
Read →
Newsletter
A letter, only when we truly have something to say.
Production insights, AI updates, and behind-the-scenes of our projects — straight to your inbox.