Addy Osmani on why agent code needs constraints, not human review

Addy Osmani argues that code review does not scale to agent-written code, so quality checks must move into the harness and environment around the agent.

He describes quality gates such as unit, property and acceptance tests, mutation testing and complexity metrics that decide whether an agent's change can ship.

He says human attention should be reserved for nuanced problems, with humans pulled in only when automated constraints break.