Blogs
AI in product
6 essays — builder-to-builder, no corporate filler.
All essays
Three Questions Before You Greenlight an AI Feature
Most AI features fail in production not because the model was wrong — but because nobody asked the right questions at scoping.
Mar 2025 · 4 min read
Stop Building AI Memory. Build an AI Memory Layer Instead.
The useful question is not which AI remembers you best. It is how to keep your memory in your own hands.
Jul 2026 · 7 min read
Opus 4.8: the benchmarks aren't the story — the harness is
Everyone's posting benchmark screenshots. The real unlock in Claude Opus 4.8 is two features they buried in the footnotes — Ultra Code and dynamic workflows — plus a quiet way to watch an army of sub-agents work.
May 2026 · 5 min read
Give Your Coding Agent Memory in 5 Minutes
agentmemory is an open-source tool that lets Claude Code, Cursor, Copilot, and other agents remember your project across sessions. Here's how to run it.
May 2026 · 4 min read
Evals Matter When You Have Stakes
Build evals when wrong outputs cost money, customers, or trust. Skip them when you can fix a bad output in five minutes.
Feb 2025 · 4 min read
The Case Against Vector Databases
Most teams that 'need' a vector database actually need keyword search and a small JSON file.
Jan 2025 · 4 min read