Works with Salesforce

    HumanhandoffforSalesforce,decidedonwhethertheanswerisright.

    You run Salesforce as your CRM and service desk. 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. Salesforce is built to be extended, so we answer inside the messaging conversations you already run.

    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 Salesforce teams run into

    Customers who have learned the automated reply is a waste of time, so they push straight through to a person and your queue never shrinks.

    “I need almost real time updates because we don't have the escalate to a live agent option right now.”
    Heather Hanson, Salesforce Trailblazer Community

    Where we sit in Salesforce

    Salesforce exposes your live conversations through Messaging for In-App and Web, and its Enhanced Chat API lets an outside service read a conversation and post into it. That is the seam we use. Your org, your routing and your omni-channel rules stay exactly as they are, and the reply arrives in the same conversation the customer is already in.

    Why this one connects

    Nothing in Salesforce insists on generating the reply text itself. It gives you the conversation and the API, and leaves the answer to whatever you connect. So we can decide what the reply should be and Salesforce can carry it.

    Source: Salesforce, Enhanced Chat API overview

    How it works with Salesforce

    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

    Do we have to change our Salesforce setup?
    No. Your objects, routing rules and omni-channel queues stay as they are. We read the conversation and post the reply into it, so nothing about how work reaches your agents changes.
    What does a handoff look like inside Salesforce?
    It becomes a normal conversation for a person, routed by the rules you already have, with the draft and the reason it stopped attached. Your agents do not learn a second tool.
    Does it work on cases as well as chat?
    The mechanism is the same wherever the conversation lives: read what was asked, find how your team answered it before, check it twice, then answer or hand over. Which surfaces we turn on is a setup conversation, not a product limit.
    Where do the answers come from?
    Replies your own agents have already sent. Nothing to write first, and no help centre to keep in sync, because the source is the work your team has already done.

    Stop the wrong answers reaching your Salesforce 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.