Blog

Thinking on AI agents, accounting, and why the two are more connected than you'd expect.

01
March 2026

What 500 Years of Accounting Can Teach AI Safety

Everyone building AI safety is thinking like an IT department. There's a better model — and it's been running since the Medicis.

Read this post
02
March 2026

Don't Build the Agent

The AI reasoning layer changes every six months. The tools layer doesn't. Most AI companies are building the wrong one.

Read this post
03
March 2026

Teach Agents How to Think, Not What to Think

Most agent builders stuff context windows with answers. The better approach is to give agents methods for finding answers.

Read this post