Customer Agent now generates knowledge from your ticket history

The feature is the easy part. Customer Agent reads your resolved tickets, drafts FAQ-style knowledge, scrubs the PII, and waits for you to approve it. If you have years of support history and no knowledge base, that is a real shortcut — and a brand new portal can get a working agent running without authoring an article first.

The hard part is the word review. Every one of these agents now ships with a human approval step, and almost nobody has decided who that human is. It could be a marketing manager, a sales ops person, a RevOps lead, a HubSpot admin, an IT person, or the partner doing the work. Different organizations have different people who ultimately carry accountability for HubSpot, right or wrong. The ones that never decide end up with whatever the agent guessed, saved in the knowledge base as if it were law — and then AI treats it as law. That is how a one-off exception you made for your biggest customer quietly becomes the policy for everybody.

This is where you switch what the humans are responsible for. The person who used to write that answer does not stop being the expert; they stop drafting and start confirming. That only works if confirming is easy. If review means copy-pasting into a Google Doc and trading comments back and forth, you are not going to build knowledge anywhere. And admins — do not take the whole thing on yourself because it is faster that way.

Start monthly, not daily. Twenty suggested knowledge moments, agree on one. You do not have to use all of them. And if your data quality and your processes are not in order yet, this is a shiny object: very valuable done right, and you have no chance of doing it right on a cruddy foundation.