Background agents still feel hard outside coding, with most actions needing prompts

menhguin · x · 2026-07-27

A discussion around “proactive background agents” for non-coding use cases says the hard part is making systems that act on their own by default, instead of waiting for human prompts.

One reply says they currently only use such an agent for read-only personal email and for setting up cron jobs to periodically check whether the model’s self-configuration is still adequate. The tone is experimental rather than confident: it is something to keep iterating on, not a polished workflow yet.

Original post →

More from coding & agent

coding & agent channel →