Plan requirement
| Subscription | Any plan |
| Access | Admin |
Yes, and email is the channel where a wrong answer costs most. Scope it before you enable it.
What is possible
An AI agent on email answers incoming tickets from your articles, in the same way as on messaging. The mechanism is the same; the consequences are not.
Why email is riskier
No clarification. The customer wrote what they wrote and has gone. A misunderstanding produces a wrong reply that arrives in their inbox as your company's considered answer, in writing, with your name on it.
On messaging they would have said "no, I meant" within seconds.
Scope it, always
Use triage topics or tags so it answers only the subjects you are confident about. Everything else reaches a person untouched.
An AI agent answering all incoming email is the configuration most likely to be switched off within a fortnight.
Decide what happens with multiple questions
Customers put three questions in one email. Answering one and ignoring two reads as not having read it, so handing over is usually the better rule.
Say that it is automated
In the reply, with a clear route to a person. Customers mind an automated answer far less than they mind discovering one was automated.
Read the first week in full
Every email the agent sent. It is a finite number at the start, and it is the only way to catch the answers that were confidently wrong.
Comments
0 comments
Article is closed for comments.