How to Work and Compound with AI

Eugene Yan · 3 May 2026 · eugeneyan.com ↗

3 korrents from this piece

Eugene Yan did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
The practices that make someone effective at working with an AI model are the same practices that make someone effective at onboarding any new human collaborator.

Their wordsnone of this is specific to AI. It's simply how you onboard and work with any new collaborator.
Our reading
Delegating a task to an AI agent only works if the output can be verified, which requires defining success criteria first.

Their wordsYou can't delegate what you can't verify, so this requires first defining success criteria and metrics.
Our reading
As AI agents take on bigger delegated tasks, the human bottleneck shifts to writing specs and reviewing output fast, hollowing out the middle of the work.

Their wordsThe bottleneck has shifted from doing the work to writing clear specs and reviewing outputs fast enough to keep the pipeline moving-the middle is hollowing out.