bluecloud.dev

AI Engineering: AI as a reviewable tool.

Agent workflows, evaluation harnesses, guardrails, permissions, logs, and the patterns that keep AI-assisted work auditable instead of opaque.

Articles

  1. Modern organizations have become very good at trying new technology and much less disciplined at absorbing it. In the AI era, the risk is not experimentation itself, but experimentation without consolidation.

  2. Useful AI in engineering keeps the same property useful tests have: a human can read what happened, where it went wrong, and decide what to do next. The argument is not that AI is dangerous. It is that anything shipping to production has to be inspectable when it fails.

Notes

  1. The reluctance to call AI evaluation harnesses tests costs more than the renaming saves. Tests get reviewed, run in CI, and have an owner. Evals deserve the same treatment.