The customer is answered
It reads the way your team writes, because that is where it came from. No queue, no wait, and no reason to go asking for a person.
You run Tidio with Lyro answering your customers. Automatifie answers from what your team has already told customers, so fewer people push for a person and fewer conversations land on your agents. When the match is not certain, a person takes over first. Lyro composes the reply itself, and Tidio gives you no way to substitute that step. Teams who want what we do move across.
We will get back to you about setting it up on your support history. By submitting you agree to our Privacy Policy and Terms of Use.
Details invented mid-answer — a phone number, a delivery window — inside a reply that otherwise reads perfectly.
“I would mention what our office number is, then when I go to review the conversation with leads, he uses some random phone numbers that aren't ours.”
More than most, and it is the closest of these to us. Lyro learns from your help centre, website, PDFs and CSVs, and its learning from historical conversations feature turns your agents' past interactions into question-and-answer pairs. So Tidio agrees with our premise: your own history is the best source.
The difference is not where the material comes from, it is what happens at send time. Lyro still composes the outgoing message, so a right source can still become a wrong sentence — which is how a number that is not yours ends up in an otherwise perfect reply. We build the reply on the stored answer, fill live details in by code rather than by model, and run a second check that asks whether it is even the same question before anything sends.
Source: Tidio, Lyro data sources
"How much is it?" on its own means nothing. Read against the chat so far it means "how much is the yearly plan". That is the question we go looking for.
Not a help article. The reply one of your own agents sent to that question, out of your support history. There is nothing for you to write first.
Their order, their plan, their delivery date, read live out of your system and dropped into the reply by code. The model never writes those values, so it cannot invent one.
Is there a close enough answer, and is it about the same thing this customer asked about. A similarity score can only tell you the first one.
It reads the way your team writes, because that is where it came from. No queue, no wait, and no reason to go asking for a person.
Before the customer ever sees a guess. Your agent gets the draft, the history and the reason it stopped.
76-90%what bot vendors advertise41%what really gets solvedHow many customer questions an AI support bot actually settles end to end, next to the number on the brochure.
Tell us what your setup looks like and we will walk you through how this fits, or tell you honestly if it does not.
We will get back to you about setting it up on your support history.