Skip to content

The moment it happens

Get alerted about low scores

When someone gives a low rating, you see their answers straight away and can follow up.

Runs
The moment it happens
Apps
Typeform
AI
Not needed
Access
webhooks:write

Send this to your assistant

Create a ClickRuntime automation: when a response to my 'Customer feedback' Typeform has a rating of 3 or less, send me the answers in Slack.

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

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

Why use it

Why teams use this automation

A customer who rates you 2 out of 10 on a Typeform survey is giving you a chance to fix things, and that chance is brief. If the low score sits in a spreadsheet until the end-of-month review, the customer has already canceled or posted a public complaint. Support managers need to hear about the unhappy ones at once, while a phone call or apology can still save the relationship.

When a response comes in, this reads the rating or NPS field, and if the score is below the threshold you set, posts an alert immediately with the score and any comment. Happy responses are not announced, so the channel only carries the cases that need a person.

It is used for NPS surveys, post-support ratings and checkout feedback. It keeps the follow-up fast.

What you get out of it

  • Unhappy customers are contacted quickly

    A call within an hour of a poor score often turns a detractor around. The same call a month later usually feels like a formality and is too late to prevent churn.

  • Specific comments reach the team

    The alert includes what the customer wrote, so support knows the reason before reaching out. That makes the first conversation about their problem, not about gathering details. Context makes the apology far more credible for everyone.

  • Only low scores are shown

    A channel full of good news hides the bad. Posting only responses below the threshold keeps the alert rare enough that people stop what they are doing to read it.

  • Patterns in complaints appear fast

    Three low scores in one afternoon mentioning the same issue signal a real problem. Seeing alerts live helps you spot a faulty release or a delivery problem on the day it starts.

  • Evidence of responsiveness

    A record of alerts and responses shows that feedback is acted on. That supports customer success reporting, and it demonstrates to leadership that survey results lead to action. Leadership sees that survey scores actually trigger something.

How it works

What happens, step by step

  1. When someone submits your feedback form, ClickRuntime reads their rating or NPS score straight away.

  2. If the score is below the threshold you set, it picks out their comment.

  3. A message goes to your #feedback Slack channel with the score and what they said, so you can follow up quickly. Good scores are left alone.

Before it runs live

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

What you get

RunsThe moment it happens
Get alerted about low scoresjust nowSucceeded
Slack · #feedbackLow feedback rating (2/5) *What could we do better?*: Exports keep timing out for our Acme account.

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 Typeform 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_feedback_alert.pyexample
from clickruntime import on_event, notify

def answers(resp):
    titles = {f["id"]: f["title"] for f in resp["definition"]["fields"]}
    out = {}
    for a in resp["answers"]:
        value = a.get(a["type"])
        if isinstance(value, dict):
            value = value.get("label") or ", ".join(value.get("labels", []))
        out[titles.get(a["field"]["id"], a["field"]["id"])] = value
    return out

@on_event
def handle(event):
    resp = (event.json or {}).get("form_response", {})
    if resp.get("definition", {}).get("title") != "Customer feedback":
        return {"alerted": False}
    rating = next((a.get("number") for a in resp["answers"] if a["type"] == "number"), None)
    if rating is None or rating > 3:
        return {"alerted": False}
    lines = "\n".join(f"*{q}*: {a}" for q, a in answers(resp).items())
    notify.slack(f"Low feedback rating ({rating}/5)\n{lines}", channel="#feedback")
    return {"alerted": True, "rating": rating}

FAQ

Common questions

What should the threshold be?
It depends on the scale. On a 0 to 10 NPS scale, detractors are 0 to 6, so many teams alert below 7. On a 5-star scale, you might alert on 2 or lower. You can adjust it later.
Does it work with Typeform's opinion scale and rating questions?
Yes, both produce numeric answers that can be compared with your threshold. You tell the flow which question to read, since a form may have several rating questions, and which one drives the alert. Pick the one that drives the alert.
Can the alert go straight to the account owner?
If the form collects the customer's email or ID, the flow can look up the owner and notify them, or post in a shared channel with the customer's details. It depends on what your form records.
What permissions does it need?
webhooks:write. 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.

Set up “Get alerted about low scores” from your assistant

Copy the prompt above, or connect your assistant first. Free plan, no credit card.