The driver’s seat however doesn’t just have to be code, as (alluded to by Charity Majors)[* https://charity.wtf/2026/06/15/ai-demands-more-engineering-discipline-not-less-xpost/], I think the drivers seat can be your observability tools, your infrastructure UI. But I think this stays the same context - don’t ask your observability AI to find the problem, query your data, learn how it’s laid out, learn the query engine.

Money Money Money Money. Monaaay!

I’m going to recommend starting with a local model, it may be slower, but it eliminates the concern of a typo or code logic error costing you hundreds of dollars (or 500 million?)

Install Ollama

On Mac, Ollama is a native app so don’t use the shell installer, download it