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.
Works with HubSpot
HumanhandoffforHubSpot,decidedonwhethertheanswerisright.
You run HubSpot as your CRM and Service Hub. 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. HubSpot's Conversations API lets us answer inside the threads your team already works, and hand one over when we should not answer it.
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.
What HubSpot teams run into
Chats that end instead of continuing when nobody is on shift, and customers left with nothing.
“It doesn't seem to matter if there is an agent available or not. The chat seems to end, leaving the user without any assistance.”
Where we sit in HubSpot
HubSpot's Conversations API gives an outside service access to inbox threads: list them, read the messages, and send a reply into a thread with the conversations.write scope. It also exposes a thread assignee endpoint, which is the documented way for a bot to hand a conversation to a person. Those are the two things our mechanism needs, so we use exactly those.
Why this one connects
HubSpot lets whatever you connect decide the reply. The handover is a first-class API call rather than a workaround, which matters here: the whole product is deciding when not to answer, and on HubSpot that decision has somewhere to go.
Source: HubSpot, Conversations API guide
How it works with HubSpot
- 01
We work out what was really asked
"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.
- 02
We find how your team answered it before
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.
- 03
We fill in this customer's real details
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.
- 04
Two checks before anything sends
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.
Then one of two things
A person picks it up
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.
Questions we get asked
- What happens when no agent is online?
- The same two checks run. If your team has answered that question before and it is clearly the same question, the customer gets the answer at 2am. If not, it goes to a person rather than ending the chat, and it is waiting for your team with the draft attached.
- Do we need to replace our chatflows?
- No. We work on the threads your inbox already produces. Your chatflows, routing and assignment rules keep doing their job.
- Which permissions does it need?
- Read access to conversation threads and conversations.write to reply into them, plus the thread assignee endpoint for handing a conversation to a person. Nothing outside your inbox.
- Where do the answers come from?
- The replies your agents have already sent in that inbox. That history is the asset, and it is why there is nothing to write before you start.
Stop the wrong answers reaching your HubSpot customers
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.