Blog

A few weeks ago I wrote about testing Jev, TypeSafe's decision model, against Claude Sonnet on a judging gate I run several times a year. Jev matched Sonnet's accuracy at roughly a fiftieth of the

The MCP spec went stateless on July 28. If you run one MCP server, that mostly means deleting your...

I went deep on automating content pipelines. At one point, I experimented with automating the content itself. I trained the system on “my voice,” read what it produced, and kept finding the same

tl;dr Know your first user, show what stands in their way, and bring evidence. You’ll get a more useful conversation. This article is for teams getting ready to present their product at Founder House

Have you ever told your agent to go do something and walked away? You set the spec clearly. You...