Integrations

Audit Intercom Fin: check every answer, and whether it held.

Connect Intercom at the level you choose, from only the conversations its AI took part in to every conversation. Each answer is checked against your help center as it stood that day, each resolution is followed for 7 days, and the patterns behind the failures come with a fix for you to approve.

What we read in Intercom

You choose how much to grant when you connect, and you can change it afterwards. It is held in our application on every read and write, not only by the access token. The rung model.

  1. 1

    Your AI’s conversations

    At rung 1 we read conversations your AI agent took part in, and nothing else. Intercom filters them before anything leaves it.

  2. 2

    Every conversation, read-only

    Your team’s answers are checked the same way as the AI’s.

  3. 3

    Approve and run

    A fix you approve is written back into Intercom. A separate choice, never where a connection starts.

From Intercom, at rung 2 and above
  • Conversations, with every message in order
  • The ratings customers left
  • Your help center articles, with every version, so an answer is checked against the article as it stood that day
  • How often each article was read
  • Your saved replies
  • Company records, so a pattern can say which accounts it reaches
  • Its AI’s own resolution outcome, kept as the vendor’s claim and never as our verdict
  • Which teammate held each conversation, for coaching one person at a time and never for a ranking
  • Who unsubscribed from email, so nobody who did is emailed from here

Intercom does not let anything outside it create saved replies, so a person adds them, with the text drafted for them.

This is what Intercom’s API allows. Your account’s plan may allow less; what is uncertain is checked with a read each when you connect, and the product says which it is reading.

What Intercom bills for its AI

What it bills
  • A resolution, whether the customer confirmed it or simply did not ask for more help.
  • A handoff to your team that one of your Procedures was set up to end in.

At most one a conversation. An escalation from Fin’s default behavior, such as a customer asking for a person, is not billed, and a resolution is taken back if the customer returns to the same conversation.

What we check

We check the resolutions. A billed Procedure handoff is not a resolution, so whether it held is not the question: we count those apart, beside the figure, from Intercom’s own record of each conversation. Intercom publishes whether it counted each one as a confirmed or an assumed resolution, and it bills for both, so that part of the review is their own number, not our interpretation.

Checked 16 October 2026 against Fin pricing: outcomes.

Whether a resolution held

A resolution is still settling for 7 days, counted neither way. After that it held unless:

  • The conversation was reopened after your vendor counted it as resolved.
  • The same customer came back about the same thing.
  • A person on your team answered after your vendor counted it as resolved.
  • The customer said it was not fixed.
  • The AI’s answer claimed something nothing in your documentation supports.
  • The AI’s answer contradicted your documentation.
  • Your vendor’s own record says its AI did not resolve this.

This is evidence that these customers did not get the resolution billed. It is not a finding that you are owed a refund; what your vendor counts and credits is set by your contract with them.

What runs in Intercom, and what a person does

At rung 3, once approved. Where Intercom’s API does not offer a step, it becomes a person’s step, with the words drafted for them. Nothing reaches a customer without a person approving the exact words.

Runs there, once approved

  • Write the article into your help center
  • Give the AI agent a precise answer
  • Raise a ticket and link the conversations
  • Message the customers this affected · reaches customers, approved word for word
  • Reopen the conversation for a person, with the evidence attached
  • Leave a handoff note for the person who inherited it
  • Write to this one customer about their conversation · reaches customers, approved word for word
  • Check the saved reply now exists
  • Ask the people affected whether it worked, through your helpdesk · reaches customers, approved word for word

A person’s step, drafted for them

  • Add the saved reply to your helpdesk

Intercom Fin reporting, QA tools, and FunctioningHQ

What a team on Intercom already has, or would look at next. Each claim about another product is from its own public pages, linked, on the date shown. Where they are stronger, we say so.

Built into Intercom

Fin’s own reports

Fin’s resolution rate, involvement rate and how each piece of content performs, with a CX Score that rates conversations, Fin’s and your team’s, from 1 to 5 without a survey (on Intercom’s Pro add-on).

Where it is stronger
  • Native: nothing to connect.
  • Its outcomes are the ones Intercom bills, so it is the closest view of your invoice.
Where we differ
  • We keep Intercom’s resolution count as Intercom’s claim and check each one against what happened next.

Checked 16 October 2026 against Fin AI Agent outcomes, Fin AI Agent reporting, The CX Score.

Built into Intercom

Fin Operator, and content recommendations

An AI agent for your team, on Intercom’s Pro add-on, that reports on resolution, satisfaction and escalation trends, works out where Fin went wrong in a conversation and drafts an article or snippet to fill the gap. Content recommendations flag content that is missing, unclear, duplicated or contradictory. A person approves every change.

Where it is stronger
  • Inside Intercom, with Fin’s settings in front of it.
  • It drafts the article or snippet itself, for a person to approve.
Where we differ
  • Every conversation you grant is checked each night, up to your plan’s monthly allowance.
  • A fix written back into Intercom is a separate grant you make. Nothing reaches a customer without a person approving the exact words.

Checked 16 October 2026 against Fin Operator FAQs, Content recommendations for Fin.

QA tool

Rippit (formerly MaestroQA)

Quality assurance for support teams: every eligible conversation scored against your rubric, with coaching built on the results.

Where it is stronger
  • A full QA program: your own rubric, every eligible conversation scored, and coaching.
  • Lists integrations for both Zendesk and Intercom.
Where we differ
  • An answer is checked against the article it should rest on, as it stood that day, rather than scored on a rubric.

Checked 16 October 2026 against Rippit: QA every support conversation, Rippit integrations.

By hand

QA in a spreadsheet

A person reads a sample of conversations each week and scores them against a rubric the team wrote.

Where it is stronger
  • Free, and the rubric is entirely yours.
  • A person reads every conversation that is scored, with all the context they carry.
Where we differ
  • Every conversation you grant is read, up to your plan’s allowance, not a sample of a few a week.
  • Each answer is checked against your help center as it stood the day it was given, and a verdict shows the passage it rests on, checked against the article.
What this adds, whichever you use
  • Each answer is checked against your help center as it stood the day it was given, and a verdict shows the passage it rests on, checked against the article.
  • Each resolution, or where the helpdesk reports none each conversation, is followed for 7 days: whether the customer came back about the same thing, said it was not fixed, or got an answer we found wrong.
  • Failures are grouped into patterns and counted in people, not conversations.
  • A fix is drafted for each pattern, a person approves it, and it is measured before and after on the people it was for.
  • Nothing scores or ranks people. Coaching speaks about one person at a time, to the manager who may see it.

Questions about Intercom

Does FunctioningHQ work with Intercom?
Yes. You connect Intercom by signing in, and choose how much to grant. At rung 1 we read conversations your AI agent took part in, and nothing else. Intercom filters them before anything leaves it. Nothing is written into Intercom until you choose to allow it, and then only what a person approves.
Will it change anything in Intercom?
Not unless you allow it. A connection starts read-only. Writing a fix back is a separate choice, and nothing reaches a customer without a person approving the exact words.
How is this different from Intercom Fin’s own reports?
Intercom’s reports are its own count of what its AI resolved, and its resolutions are part of what it bills. We keep that count as Intercom’s claim and check each resolution against what happened next, and each answer against your help center.
Can I try it for free?
Yes. Up to 500 of your recent conversations, read once and checked, ending on what to fix first. No card.

Start with a free audit of your Intercom.

Up to 500 of your recent conversations, read once and checked, ending on what to fix first. No card.

Request beta access