Plan requirement
| Subscription | Any plan |
| Also required | AI agents - Advanced |
| Access | Admin |
Past conversations can teach the agent how your customers actually ask. Powerful, and it needs a decision about what you feed it.
Import it
- Open the AI agent's training settings.
- Choose the historical conversations to use.
- Start the import.
- Review what it derived before acting on it.
What this gives you
The phrasing customers really use, and the frequency of each subject. That is information you cannot get from your own imagination, and it usually contradicts the internal names for things.
It is as valuable for deciding what to document as for the agent itself.
Choose the period deliberately
Recent conversations reflect the current product; old ones describe how things used to work. A year is usually the right window, and less if you have changed something significant.
Old answers were not all correct
Historical exchanges include agents who were mistaken, policies since changed, and workarounds no longer needed. Treat the import as a source of questions rather than a source of answers.
Think about what is in them
Real conversations contain real customer details. Consider what your tickets hold before importing them, and involve whoever is responsible for that decision in your organisation.
Read what came out
The subjects it identified are a report on your support operation. Anything frequent and undocumented is an article to write, and that list is worth more than the training itself.
Comments
0 comments
Article is closed for comments.