Experiments and questions about local AI, agents, browser automation, and responsible tool use.
RAG for Small AI Applications - Retrieve Evidence Without Treating It as Truth When a language model answers a question about a private document, a product manual, or a changing internal policy, there is an uncomfortable gap between what the model knows and …
Read article
There is a piece of jargon that shows up in almost every conversation about connecting an AI assistant to real software: MCP. The Model Con…
A small application reads an incoming email, asks a language model to summarize it, and then, if the summary mentions a task, lets the mode…
A language model can return neat JSON instead of a paragraph. That feels like a decisive step toward reliable automation: the keys are pres…
A browser test passes on a laptop, fails in continuous integration, and passes again when retried. Is the application broken, is the test i…
Some time ago I was stuck thinking about one thing: AI chatbots are actually just machines that answer questions. He can explain how to coo…
I still remember the first time I ran local LLM on my used laptop. It's like just building a personal assistant in the corner of your room:…
A few months ago, I was proud to have a local AI Assistant who could answer everyday questions. Ask about Nginx, he answers. Ask about Pyth…
Some time ago I wrote about personal fitness tracker that I built with Next.js and Supabase. This time I want to tell you about a toolki…
