The moment it happens

Get alerted about bad conversation ratings

When a customer rates a conversation 1 or 2 stars, you see it with their comment right away.

Runs: The moment it happens
Apps: Intercom
AI: Not needed
Access: read conversations

Send this to your assistant

Create a ClickRuntime automation: when someone rates an Intercom conversation 1 or 2 stars, post the rating, their comment and a link to #support in Slack.

Paste it into your assistant. It tells you what it will send or change before it runs live.

Add to ChatGPT Add to Claude

First time? Adding ClickRuntime to your assistant takes about two minutes.

Why use it

Why teams use this automation

A customer finishes a chat with your support team and clicks two stars, adding a remark: "Third time I've explained this and nobody fixed it." That rating goes into Intercom's reports, where it is averaged with hundreds of happy ones and read, if at all, at the end of the month. The customer has already decided whether to renew, and nobody on your side knew to reach out while it could still matter.

When a customer submits a rating in Intercom, ClickRuntime receives it right away. If the score is 1 or 2, it fetches the conversation and posts the rating, the customer's remark and a link to the conversation in Slack. Ratings of 3 and above are ignored, so the channel stays quiet unless there is a real problem.

It is most useful to support managers and customer success leads who want to rescue unhappy customers personally.

What you get out of it

Unhappy customers get a personal follow-up
A manager who writes to a customer within the hour, acknowledging the problem and offering a fix, can often reverse a bad impression. The same message a month later is too late to matter.
Churn signals reach the account owner
A low rating from a key account is a leading indicator of cancellation. Posting it where customer success and sales can see it lets them step in before the next renewal conversation.
Remarks reveal what actually went wrong
Customers say why they are unhappy in plain words, and those words are usually more useful than the score. Having the remark in front of you immediately tells you whether the issue was a slow reply, a wrong answer or a product bug.
Coaching moments arrive while fresh
An agent can review a poorly rated conversation the same day, when they still remember it. Feedback given then is specific and easy to accept, compared to a quarterly review of old transcripts.
Bad ratings stop hiding in averages
An average of 4.6 can conceal a handful of angry customers who will never come back. Isolating the worst ratings makes them impossible to overlook, regardless of how good the overall figure looks.

How it works

What happens, step by step

When a customer rates an Intercom conversation, ClickRuntime picks it up straight away.
If the rating is two stars or lower, it fetches the conversation.
A message goes to your #support Slack channel with the rating, the customer's remark and a link to the conversation.

Before it runs live

Connect Intercom
Paste your automation's link into the other app's webhook settings

What you get

RunsThe moment it happens

Get alerted about bad conversation ratingsjust nowSucceeded

Slack · #support1★ rating: Waited two days for a reply about a failed payment.

Build your own

Need it to work differently?

This template is a starting point. Copy the prompt and change it, or describe a different automation from scratch, with your own conditions, more apps or an AI step. Your assistant writes it, tests it and runs it on ClickRuntime.

Your own rules
Conditions, thresholds, filters and exceptions, written the way you'd explain them to a colleague.
Any number of apps
One automation can read from one app and update several others. Over 248 apps are ready, and anything with an API works too.
AI where it helps
Summaries, classification, extraction and drafts use ClickRuntime's built-in AI, with no extra key.
On a schedule or on each event
Runs as often as every 5 minutes, or the moment an app sends an event, and keeps track of what it already handled.

Changes you can ask for

Act only on the items that match your own rules, and skip the rest
Add an AI step, for example to summarize, sort or draft a reply
Add another app, for example also send it to Slack
Combine it with other Intercom steps into one automation

Under the hood

The code that runs this automation

This is the Python script that runs each time the automation starts. Your AI assistant writes it for you when you send the prompt, and you allow each step in your assistant. To change how the automation works, describe the change to your assistant and it updates the script for you. For every function it can use, see the script reference.

bad_conversation_rating_alert.pyexample

from clickruntime import on_event, notify

INBOX = "https://app.intercom.com/a/inbox/_/inbox/conversation/"

@on_event
def handle(event):
    body = event.json or {}
    if body.get("topic") != "conversation.rating.added":
        return {"posted": False}
    convo = body["data"]["item"]
    rating = convo.get("conversation_rating") or {}
    if (rating.get("rating") or 5) > 2:
        return {"posted": False}
    notify.slack(f"{rating['rating']}★ rating: {rating.get('remark') or '(no comment)'}\n{INBOX}{convo['id']}", channel="#support")
    return {"posted": True}

FAQ

Common questions

What rating scale does Intercom use?

Intercom's conversation ratings use a scale of 1 to 5, often shown as faces or stars, depending on how you set it up. This alert reacts to scores of 1 or 2, which are the lowest two choices on that scale.

Can I change the threshold to include 3-star ratings?

Yes. If a 3 is a warning sign for your team, ask for the alert to include ratings up to 3. The more scores you include, the busier the channel will be, so many teams start with 1 and 2 and widen it later.

What if the customer leaves a rating without a remark?

The alert still posts, with the score and the link, and the remark section simply shows that none was left. Many customers click a low score and say nothing, so the link to the conversation is the way to see what happened.

What permissions does it need?

read conversations. Nothing else in your accounts is used.

Does it need AI?

No. It runs without AI, so it doesn't use your plan's AI allowance.

How many runs does it use?

One run for each event the app sends.

Can I change how it works?

Yes. Describe the change to your AI assistant, for example a different schedule, channel or filter. It updates the automation, tests it and tells you what changed.

The moment it happens