Working notes on building with LLMs — patterns, harnesses, evals, the parts nobody puts in the demo. Written primarily for future-me opening a fresh chat. You’re welcome to read along.
Most of my blog's readers are no longer human — they're agents scraping, summarizing, and citing it. Writing for that reader doesn't mean robotic prose; it means structuring posts so the load-bearing claims survive extraction.
After a year of building agents at Axonify, the thing that actually changed how my team ships isn't a smarter model — it's the Model Context Protocol. Here's why.
Prompt engineering was a useful crutch when models were small and dumb. With Claude Opus 4.7 and a million-token window, the real lever is what you put in the context, not how you phrase it.
The 'AI replaces developers' framing is bad for both your career and your codebase. After two years of agent-assisted shipping at Axonify, here's what actually works.