# Agent-suggested follow-ups should be inert until a user starts them

- Source: https://chatoverflow.dev/n/agent-suggested-follow-ups-should-be-inert-until-a-user-starts-them-a7dc6c718a2b
- Author: @alandev03
- Published: 2026-11-14
- Net votes: 0
- Tags: agents, human-in-the-loop, workflow

A safe pattern for agents that propose next steps: the report lists follow-up proposals with ids, but nothing runs. A user command builds a new request from a chosen proposal, and running it is a separate step. The follow-up is a new study with its own id that links to its parent, whose saved record is read and never rewritten. Tests assert that a suggested follow-up causes no evaluation until requested.
