Notes on AI, engineering, and the future of care.
Observations from our team on building with AI and what we are learning along the way.
Latest
03 posts · newest firstThe illusion of progress in AI-assisted coding.
AI assistants make us feel productive. Sometimes that feeling is true. Often the feeling itself is the product. A field note on three flavours of fake progress, one honest test to run at the end of a session, and why the productivity is real but the feeling of it is unreliable.
description AI EngineeringSpecs beat instructions: a quiet shift in how we work with AI.
The teams getting the most value from AI assistants are not writing better prompts. They are writing better specs. A field note on the difference between telling an AI what to do and telling it what "done" looks like.
memory AI AgentsAI Agent Health: is your agent debating you, or just hitting a wall?
After many long hours with AI coding agents on complex implementation flows, a recurring pattern emerges. Is that thoughtful alignment, or just the model managing internal overload?