Plan requirement
| Subscription | Suite Team or higher, Support Team or higher |
| Access | Admin |
Where AI agents are built and watched. Knowing which part answers which question saves a lot of clicking.
The parts
- The agent list, showing what exists and what is live.
- Replies and dialogues, what the agent says and the exchanges it can carry.
- Use cases and procedures, the situations it should recognise and the steps to follow once it has.
- Knowledge, which content it may answer from.
- Actions, what it can do in other systems.
- Channels, where it appears.
- Conversations, transcripts of what happened.
- Reporting, the numbers on top of those conversations.
The one to spend time in
Conversations. Everything else describes what you intended; transcripts show what customers got.
Reading ten of them teaches more about your AI agent than any dashboard, and it is the habit that separates a working deployment from one that quietly disappoints.
Testing sits next to building
You can try the agent as you configure it, without touching what customers see. Use it constantly: a change that reads sensibly often behaves differently in an actual exchange.
Changes are live once published
Edit a reply and publish, and the next customer gets it. There is no staging environment here, which is another reason to test in the workspace before publishing.
Knowledge is a scope, not a copy
Pointing an agent at your help centre does not duplicate the articles. It searches the current content at the moment it searches, so publishing an article makes it available and unpublishing removes it, with nothing to sync.
That holds for a help centre and not for anything else. An external knowledge source, brought in by a web crawler or a knowledge connector, is searched as it stood at the last sync rather than as it stands now. How far behind that can be depends on the route: a web crawler syncs on a frequency you set, weekly by default, while the universal knowledge connector does a full refresh every twenty-four hours and is not a setting. So a correction on your own website waits for the next sync, while the same correction in an article is immediate.
Comments
0 comments
Article is closed for comments.