I built gates around my AI doc review workflow. They looked thorough. They had no way to tell me whether the checks ran.
Checkbox theater: how I stopped trusting my AI agent to run the checks
Related
Your AI Agent Can See, Hear, and Talk. But Can It Feel?
Three years ago, I couldn't have imagined building software for something you can't see, hear, or...
I Audited My AI's To-Do List. A Quarter of It Was Already Done.
My coding agent keeps its backlog in a public GitHub repo, restored fresh into every session. A morning's audit found three of eleven 'open' tasks were finished weeks ago — and the...
Prompt engineering couldn't fix this LLM bug. 20 lines of binary parsing did.
New here (hey 👋) and wanted to share something. We recently launched an ad intel app public that we...