"The agent hallucinates" is a bad diagnosis: it sends you looking at the model. On an agent extracting data from documents, I watched the guarantee move — from model quality to three engineering constraints. One of them surprised me.
Family apps are very good at filing a household's information. None of them change who has to think about it. Building Noan, I spent more time on that shift than on every feature combined — and on the tightrope it forces: making invisible work visible without keeping score.
They say it takes 14 steps to become an agentic AI engineer. Spoiler: real transformations fit into 5 architectural patterns. Here's how I learned it's no longer about talking to the model, but building a system that decides.
Perplexity is pulling back from MCP internally, and their reasons are real. But token bloat and weak permissions are a wiring problem, not a protocol one. Here's a POC that exposes my tools once and grants each agent only its slice.
Ti Boug, my iPhone app against the cost of living in Réunion: the real daily prices of fruit & veg, their season, and an AI-composed basket — from the official DAAF price bulletins. What it does, the stack, and where the build stands.
LangChain ships deepagents: the four building blocks I've been repeating for three months, named and packaged. I test them on a real personal need — a banking companion, my statement PDFs kept local, a real chat UI — and find out the pillar that matters isn't the one I expected.
No crash, no log, just white. Three different causes, one symptom — plus the 4th bug that made the other three impossible to debug: my safety net had a hole in it.
I'm building an app for Réunion: the real price of fruit and veg already exists, public, stuck in PDFs nobody reads. Ti Boug sets it free — what's cheap, where, and when. The build, and why I challenge the idea before believing it.
The 3000 most useful English words, ordered by frequency, as flashcards with spaced repetition. It all lives in the browser, the data is the single source of truth, and it's online on GitHub Pages. The story of a mini-app designed to last with zero maintenance.
Three frontier models, 72 group-stage matches, predictions frozen before kickoff, and a leaderboard that updates itself. A benchmark dressed up as a game — and the perfect excuse to ship a quick mini-app on GitHub Pages.
Astro 6, Tailwind 4 with @theme, content collections + MDX, bilingual FR/EN, and a full GEO setup (llms.txt, JSON-LD entity graph, robots.txt with allow for AI bots). How and why I rebuilt it all.
You talk for 30 seconds. Whisper transcribes, Claude writes your journal, gives you a Mind Score and tags your emotions. Here's how it's built and why I did it.