Experiments and questions about local AI, agents, browser automation, and responsible tool use.
A prompt is revised, a newer model is selected, or a retrieval setting is adjusted. The first few outputs look cleaner than before. Is the workflow actually better, or did the demonstration simply avoid the cases that became worse? This is the practical role…
Read article
An AI application that drafts an email and one that sends the email may use the same model, but they do not carry the same kind of authorit…
RAG for Small AI Applications - Retrieve Evidence Without Treating It as Truth When a language model answers a question about a private do…
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…
