L'Atelier.
Notes sur l'automatisation du navigateur, l'IA locale et la construction en public.
Derniers articles
Affichage : toutes les catégories
IA localeWhy vector search misses exact terms, and what hybrid search fixed (measured)
Ask a vector search for ERR_4521 and you may get ERR_4512. How we added BM25 next to vectors with reciprocal-rank fusion in an in-browser knowledge base, what we measured, a SurrealDB full-text gotcha, and a filtering bug that gave small collections zero hits.
ProduitWorkflows that survive a closed tab: durable waits with checkpoints and chrome.alarms
How a browser-extension workflow can pause for up to 30 days, survive a closed tab, a browser restart or an extension update, and resume where it stopped: checkpoints in storage, wake-ups owned by chrome.alarms.
ProduitYour browser is quietly an operating system: the 4 WebAssembly engines in our extension
One Chrome extension, no backend for its core features: a real database, two AI inference engines and a full Python interpreter, all running as WebAssembly. What each engine does, how it's wired, and what it costs.
ProduitYour context window is a budget, not a bucket
Most context-window bugs come from one assumption: the prompt is the chat history, so cut the oldest messages. In an agent, history is often the smallest part. Seven rules for budgeting a prompt, from a 128k cloud model down to a 2,048-token model in the browser.
IA localeAWFlow veut devenir l'OpenRouter de l'IA qui tourne dans votre navigateur
Trois moteurs d'IA pour navigateur, trois formats de modèles incompatibles. AWFlow se place devant les trois pour que vous choisissiez un travail, pas une bibliothèque. Où nous en sommes et pourquoi le web y arrivera.
TutorielsComment utiliser l'IA gratuite dans AWFlow : Agents, Chat et Automatisation sans clé API
Installez un modèle d'IA locale une fois et il alimente tout AWFlow : l'assistant chat, vos agents et vos workflows d'automatisation. Un tutoriel pratique, étape par étape.
IA localeDo you need a big AI model? A one-hour test that tells you
The biggest model is a habit, not a requirement. How to tell which of your automation jobs a small, free, on-device model can handle, with a simple test on your own inputs that takes about an hour.
IA localeFree AI vs API-key AI: what an automation really costs
How to estimate an AI step's cost before you build it, why the page you feed in is usually the bill, and a simple design that sends only the hard work to a paid model. With a calculator for your own numbers.
TutorielsHow to pick a local AI model your laptop can actually run
One number decides whether an AI model runs on your laptop: the memory it needs. How to read model names like q4f16_1, why every fit label is an estimate, and how to install, test and keep a model, step by step.
ProduitLangChain and LangGraph in the browser: how an AI agent builds your workflow
An agent is not one big prompt. It is a graph of steps with branches, loops and a memory of where it paused. Here is how that works, with the real graph behind AWFlow's assistant.
ProduitLe problème des 5 onglets : laissez votre navigateur faire le copier-coller
Une petite tâche, cinq onglets : le prix d'un concurrent, une deuxième boutique, un tableur, un assistant de chat et votre boîte mail. Voici pourquoi cela finit par coûter cher, et comment un seul workflow dans votre navigateur s'en charge pour vous.
IA localeThe airplane-mode test: the only privacy proof for AI you can run yourself
Every AI tool says it respects your privacy. One test settles it: switch off the internet and see if it still works. What offline AI really requires, how a workflow can fail the test, and how to run it in five minutes.
Aucun article ne correspond à cette recherche.
Une lettre par mois. Sans bruit.
Nouveaux articles, modèles à copier sans hésiter et nouveautés livrées. Désabonnement en un clic.