The founder of a podcast hosting company shared his Hermes Agent and knowledge base with his team, starting with support. Its first automated scan of new tickets suggested six help doc updates and two marketing posts.
- First reported
- x.com · 27 Aug 2026
- Added
- 13 Oct 2026
- Source checked
- 13 Oct 2026
What they did
He opened the agent to his support and development staff and set up a recurring scan of incoming support tickets. For each batch, the agent looks for questions that point to a help doc that should be improved or created, and for topics that deserve a new or updated blog post on the website. He also set up daily backups of the whole agent setup to a company GitHub repo.
What happened
The first scan produced six help doc suggestions and two marketing suggestions.
Keep in mind
He had not yet decided how suggestions get validated and acted on, possibly as GitHub issues. This was day four of the rollout, so impact on ticket volume is unknown.
Try it with your agent
Every <day or time>, read the new support tickets in <your helpdesk> since the last run. Group them by question, then list which existing help articles in <your help center> should be updated, which new articles we need, and which topics deserve a blog post. Link the tickets behind each suggestion and do not publish anything.
Replace the <angle brackets> with your own details.
Original source
x.comUser storySomeone who uses the agent described their own setup. Figures are theirs.
Tools for this kind of work
The whole toolkit →
