Posts

All the articles I've posted.

• The handoff is the part nobody writes down

  9 Sep, 2025·22 min read

  Leaving a fleet of LLM agents a client's own team can run: discovery by directory, scorecards a stranger can read, runbooks drilled against real failures.

• Faithful to the wrong version

  17 Jun, 2025·26 min read

  On a versioned corpus, faithfulness metrics pass an answer grounded in a revision retired months ago. Treating the corpus as bitemporal is what fixes it.

• Text-to-SQL that can't leak data it shouldn't

  18 Mar, 2025·25 min read

  The seam between what a model may see and what it may run, enforced by different systems owned by different teams, and the error message as a leak channel.