Notes

Six essays on what agents don't know, newest first. If you only read one, read Too small to tell. Oldest first if you want the argument to build.

  1. Aug 2026Too small to tell. Say so.I built an agentic system that runs marketing experiments end to end. Its most valuable output was a refusal to answer.7 min · ★
  2. Jul 2026Your agent works. Prove it.A single run isn't a measurement. Agents are nondeterministic, most teams score them as if they aren't, and the number that ends up on the slide is often quietly dishonest.5 min
  3. Jun 2026Show, don't tell.No, AI isn't making product management obsolete. It just let me stop telling people things and start showing them.3 min
  4. May 2026Nobody gave it the address.Your agent logic is probably fine. The information underneath it isn't. That's the job now.5 min
  5. May 2026I asked Claude to build my MCP server. Here's what I actually got.Standing up an MCP server took a day. Understanding what I built took longer. The interesting part wasn't the engineering.6 min
  6. Apr 2026Don't build the agent. Enable the access.Why the next twenty years of product work is about exposing capabilities to agents, not designing destinations for users.7 min
Reading times include the dog.