Ask HN: How are you designing human review for production AI agents?

A Hacker News user asks how developers design human review for production AI agents, specifically what actions are automated versus requiring human approval and how to keep the process auditable. A commenter notes that the review loop can expand from one human reviewing AI output to six people reviewing the review process.

Hacker News new | past | comments | ask | show | jobs | submit login Ask HN: How are you designing human review for production AI agents? 2 points by willXare 15 minutes ago | hide | past | favorite | 1 comment For people running agents in real workflows: what do you let the agent do automatically, what requires human approval, and how do you keep the review process auditable? help pfannl 10 minutes ago – The loop starts with one human reviewing AI output and ends with six people reviewing the review process. reply Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search: