Addy Osmani: Agent Code Quality Depends on a Validation Loop

Addy Osmani argues that the key to agents writing code that is “better on average at scale” is validation, because agents make checking cheap. The tests, benchmarks, specs, and real end-to-end runs that used to make “good code” expensive can now be handled directly by agents, so the focus shifts from line-by-line review to building loops the agent can run on its own, giving it the means to verify its work. He also suggests writing the mistakes an agent has made into shared config, hooks, or tests so the experience compounds. Humans are still accountable for shipping, but they look at evidence rather than just the diff.