Hermes Agent · Nous Research
Scan new support tickets for help doc and blog post ideas
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.
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.
How it went
The first scan produced six help doc suggestions and two marketing suggestions.
Worth knowing
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 Hermes 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 Link the tickets behind each suggestion and do not publish anything.
Swap the parts in angle brackets for your own details. This prompt is adapted from the case, not copied from the original.
What this label means: User story
Someone using it at work posted about it. Any numbers are theirs, so we write "the poster says".
Summarised from the original source; the link has the full story. The people and companies here are not Wize customers.