The moment it happens

Spot frustrated comments on customer issues

When a comment on a customer issue sounds frustrated, you hear about it before it escalates.

Runs: The moment it happens
Apps: Linear
AI: Yes, uses the built-in AI allowance
Access: read

Send this to your assistant

Create a ClickRuntime automation: watch new comments on Linear issues labelled customer, and Slack me the comment and issue link when it sounds negative or frustrated.

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

Support teams that track customer issues in Linear see frustration build in the comments. A customer who has waited a week for a fix writes something sharper each time, and an engineer who works the ticket sees only the most recent message. By the time a manager notices the tone in a comment thread, the customer is already thinking about canceling.

When a comment is added to an issue with the support label, ClickRuntime sends the text to its built-in AI, which judges whether the writer sounds frustrated or upset. Neutral and positive comments are ignored; negative ones are posted to Slack with the issue link and an excerpt, so a manager can step in while it is still recoverable.

It helps customer success leads and support managers who watch many issues at once.

What you get out of it

Unhappy customers are caught early
A manager who sees a frustrated comment on day three can call the customer and reset expectations. The same comment found on day ten is usually the last straw before a cancellation.
Escalation depends on tone, not guesswork
Priorities on tickets rarely capture how a customer feels. A signal from the actual words shows who is getting angry, even when the issue was labeled low priority. That is the difference between a calm customer and a lost one.
Engineers get context about the person
Knowing that the customer behind an issue is losing patience changes how an engineer handles it. A quick workaround or an honest update may be all that is needed. Small gestures of care often change the outcome of a hard ticket.
Support leads cover more tickets
One manager cannot read every comment on every issue. An alert for only the negative ones directs attention to the small portion that needs it. Attention goes where it makes the most difference.
Recurring pain points surface
If frustration keeps appearing on issues about the same feature, you have evidence for prioritizing a fix. The Slack history becomes a record of where customers hurt most. That evidence is hard to ignore in planning.

How it works

What happens, step by step

When someone comments on a Linear issue, ClickRuntime checks whether the issue carries your customer label.
AI reads the comment and decides whether the tone is frustrated or negative.
Neutral and positive comments are ignored.
Frustrated comments are posted to your #customers Slack channel with the issue ID and a quote, so someone can step in quickly.

Before it runs live

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

What you get

RunsThe moment it happens

Spot frustrated comments on customer issuesjust nowSucceeded

Slack · #customersFrustrated comment on ENG-544: > Third week waiting on this, Acme is asking daily.

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
Change what the AI looks for, or how it writes the result
Add another app, for example also send it to Slack
Combine it with other Linear 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.

negative_sentiment_comment_alert.pyexample

from clickruntime import on_event, http, credentials, ai, notify

def linear(query, variables=None):
    r = http.post(
        "https://api.linear.app/graphql",
        headers={"Authorization": credentials.secret("LINEAR_API_KEY")},
        json={"query": query, "variables": variables or {}},
    )
    r.raise_for_status()
    return r.json()["data"]

@on_event
def handle(event):
    body = event.json or {}
    c = body.get("data", {})
    if body.get("type") != "Comment" or body.get("action") != "create":
        return {"alerted": False}
    issue = linear("query($id: String!) { issue(id: $id) { identifier url labels { nodes { name } } } }",
                   {"id": c.get("issueId")})["issue"]
    if "customer" not in [l["name"].lower() for l in issue["labels"]["nodes"]]:
        return {"alerted": False}
    mood = ai.generate(f"Is this comment negative or frustrated? Answer yes or no.\n{c.get('body', '')[:1500]}",
                       max_output_tokens=5).text.strip().lower()
    if not mood.startswith("yes"):
        return {"alerted": False}
    notify.slack(f"Frustrated comment on {issue['identifier']}:\n> {c.get('body', '')[:500]}\n{issue['url']}", channel="#customers")
    return {"alerted": True}

FAQ

Common questions

How does it judge sentiment?

It sends the comment text to ClickRuntime's built-in AI and asks whether the tone is negative. Polite complaints may pass while clear irritation is flagged. Because the excerpt is in the Slack post, a person always makes the final judgment. Tell your assistant which labels count as support issues so the check stays focused.

Does it read comments on every Linear issue?

No. It filters by the issue label you choose, such as support or customer-reported, before any AI step runs. Internal engineering comments are not analyzed, which also avoids false alerts from blunt technical discussion. This keeps costs and noise down.

Will it flag a comment written by my own teammate?

It can, since it looks at the text, not the writer. If you want only customer-written comments checked, you can ask to skip comments from your team's accounts or from a specific bot user, so only the customer voice triggers alerts.

What permissions does it need?

read. Nothing else in your accounts is used.

Does it need AI?

Yes. It uses ClickRuntime's built-in AI, so you don't need an OpenAI or Anthropic key. Every plan includes a monthly 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 happensAI