Works with Voiceflow

    HumanhandoffforVoiceflow,decidedonwhethertheanswerisright.

    You run Voiceflow to design and run your agent. 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. Voiceflow's API step calls out to us mid-conversation, so the flow you designed stays the flow that runs.

    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 Voiceflow teams run into

    A designed flow that still has to guess on the questions nobody drew a path for.

    Where we sit in your agent

    Voiceflow's API step calls an external endpoint, saves the response to a variable, and lets you pull a specific field out of the JSON. So the step calls us, stores what comes back, and your canvas branches on it: send the answer, or take the path you drew for a person. The decision is visible on the canvas rather than hidden in a model.

    Why this one connects

    Voiceflow is a design tool, not a closed answer engine. It expects to call outside services for the parts it does not decide itself, and what the reply should be is one of those parts.

    Source: Voiceflow, API step docs

    How it works with Voiceflow

    1. 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.

    2. 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.

    3. 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.

    4. 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
    Both checks pass

    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.

    Either check fails

    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 advertise
    41%
    what really gets solved

    How many customer questions an AI support bot actually settles end to end, next to the number on the brochure.

    Questions we get asked

    Does this replace my Voiceflow agent?
    No. Your flows, intents and the paths you designed all stay. We answer the open questions your canvas cannot enumerate, and hand back to your designed path when we should not answer.
    Where does the handoff path go?
    Wherever you already send people. We return a handoff and a reason to a variable, and your canvas takes it from there.
    Does it slow the conversation down?
    It is one API step. If you would rather not block on it, Voiceflow's async toggle lets the flow continue while the call completes.
    Where do the answers come from?
    Transcripts your team has already handled, not the flow content. That is the difference: your canvas covers the paths you thought of, and the answer base covers the questions you did not.

    Stop the wrong answers reaching your Voiceflow 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.