When a customer asks a question, the AI answers from the knowledge sources you point it at — an AB wiki and public help content — and cites what it used. Anything it can’t ground in those sources, it hands to your team instead of guessing.
The two source types
AB wiki
Your team’s own documentation. Leave the project id blank to use this desk’s own wiki, or enter another project’s id (say, an AB Projects project) to reuse knowledge you already wrote.
Public help content
Help-centre articles, like this one. Leave the channel id blank for the default help channel, or point it at your own. Great for the how-tos and FAQs your customers already read.
Each source can be turned on or off, and repointed, per desk — you do it in Settings. Because it’s per desk, a billing desk and a technical desk can answer from completely different material.
How answers stay trustworthy
The AI answers only from the sources you give it, and shows the articles it drew from beneath each reply. If the sources don’t cover the question, it says so and routes the ticket to a person rather than inventing an answer — see how a ticket works.
Keeping them healthy
- Watch the escalation rate. A low Handled by AI % on the dashboard usually means thin sources, not a bad AI.
- Watch the helpfulness score. Lots of answers with a poor rating means the AI is confidently answering from content that’s wrong or unclear — fix the source, not the prompt.
- Review after any change customers care about. New pricing, a changed policy, a discontinued product — update the source the day it changes, because the AI will keep quoting the old one until you do.