OpenAI Decisions vs. Jev: notes from the failures
Both repeatedly picked the wrong implementation file. Routing, history, and marketing checks gave me different reasons to prefer each API—and reasons to check both.
Writing
Wrangling Agents With Repeatable Tools
I don't need an agent to invent a new way to run my tests or triage a PR every time. Extracting those procedures into code gives me reusable tools, smaller agent jobs, and results I can inspect. It can also give me a very elaborate way to waste time.
Putting Old Bible Study Notes Back to Work
I had already done much of the thinking. AI helped assemble the supporting material, take away the blank page, and turn my teaching notes into a handout.