Writing · Published

Notes on Useful AI

A working set of principles for using language models in serious knowledge work without surrendering judgment.

AI workflows · Knowledge work

I am less interested in whether an AI system appears intelligent than in whether a workflow produces better, more inspectable work.

A few provisional principles

  1. Give the model artifacts, not just instructions.
  2. Keep consequential decisions visible and reversible.
  3. Separate collection, interpretation, and synthesis.
  4. Verify outputs in proportion to the cost of being wrong.
  5. Prefer workflows that improve human understanding as they run.

These principles are not a policy. They are a practical filter for experiments: does this arrangement help someone see and decide, or does it merely create more fluent output?