Peter D. Bethke https://peterdbethke.com Writing on AI agents, access control, and verification. Where the boundary lives https://peterdbethke.com/writing/where-the-boundary-lives/ https://peterdbethke.com/writing/where-the-boundary-lives/ Who may write, what they may write, and the place I put the boundary that an agent walks straight past. Sun, 23 Aug 2026 00:00:00 GMT Your codebase is the prompt https://peterdbethke.com/writing/your-codebase-is-the-prompt/ https://peterdbethke.com/writing/your-codebase-is-the-prompt/ Coding agents do the unglamorous groundwork when building from scratch — and skip it in code where someone else already did. Mon, 03 Aug 2026 00:00:00 GMT An agent that can answer anything can be trusted about nothing https://peterdbethke.com/writing/trusted-about-nothing/ https://peterdbethke.com/writing/trusted-about-nothing/ Bounding a corpus, not widening it, is what makes an agent testable — and the difference between context that is retrieved and context that is injected is the whole of it. Sat, 01 Aug 2026 00:00:00 GMT Build your competitor as an agent — then find out what you told them https://peterdbethke.com/writing/build-your-competitor-as-an-agent/ https://peterdbethke.com/writing/build-your-competitor-as-an-agent/ Ground an agent only on what an outside analyst could actually assemble about you, then point the same collection at your own company. Thu, 30 Jul 2026 00:00:00 GMT