Supportman (@supportmanHQ) header
Supportman (@supportmanHQ) profile picture

Intercom CSAT, AI scoring + weekly reports, in Slack. What separates a 1-star reply from a 5-star one. #custserv #cx

Joined February 2020
Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)Photo by Supportman (@supportmanHQ)
Supportman puts your Intercom CSAT in Slack, in real time. Bad ratings get their own channel. Friday reports for the team, DMs for each agent. And AI QA that scores every closed conversation — including the ones customers never rated.
1
1
157
Intercom has two features called "topics." They don't talk to each other, and mixing them up wastes setup time.
1
20
Fin's Topics Explorer: AI-generated, zero setup, shows what Fin thinks customers are asking about right now. A separate system entirely.
1
3
Fin doesn't need the same QA rubric as a person. It needs its own, because it fails in different ways.
1
17
Run it weekly on a sample, not once a quarter on everything. That's the difference between catching a regression and reading about it in a churn interview.
1
9
Andrew "Coach" Rios, on the report that changed how he writes them. A product manager once told him: "Great report. I don't know what to do with it, though." Episode: supportman.io/live-chat/coac…
1
6
Steph Hardy (Guru) ran sprints for her CX team and found the real gap wasn't volume data: "There was no actual context, that qualitative context of what's happening on those calls." Episode: supportman.io/live-chat/agil…
1
4
A report with no action item is just a status update. A log with no context is just a number. Neither changes what anyone does next.
2
Intercom Reports does volume, response time, and CSAT on rated conversations well. Real talk on what it doesn't do:
1
6
And once you spot a pattern, there's no built-in path to escalate it. You're back to a manual message.
1
1
Meg Palazzolo, building with AI: "Didn't get it right the first time." Episode: supportman.io/live-chat/ai-a…
1
12
One builds with AI, one writes with it. Both treat the first output as a draft, never the finished thing.
2
Your Intercom CSAT report is smaller than you think: rated conversations only. Most customers never leave a rating at all.
1
12
The split that matters most right now: Fin vs human. Blend them and a Fin regression can hide in your CSAT for weeks.
1
2