Skip to content

Collects as they arrive, acts daily

Find out why customers cancel

Cancellation feedback is sorted into reasons, and each month you get a breakdown.

Runs
Collects as they arrive, acts daily
Apps
Stripe
AI
Yes, uses the built-in AI allowance
Access
read

Send this to your assistant

Create a ClickRuntime automation: when a Stripe subscription is cancelled, sort the cancellation feedback and comment into a reason like price, missing feature or switched tool, and email me a breakdown on the 1st of each month.

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 SaaS founder sees 40 cancellations in a quarter and a pile of free-text answers in Stripe's cancellation_details: too expensive, switching to a competitor, missing an export feature, just testing. Nobody has time to read them all and tag them by hand, so the loudest anecdote wins the next roadmap meeting. Real reasons for churn stay unmeasured, and pricing or product decisions rest on guesses.

As cancellations arrive, ClickRuntime reads the cancellation reason and comment from Stripe, has ClickRuntime's built-in AI place it in a category such as price, missing feature, support, competitor or no longer needed, and increments a counter for that category. Once a month it emails you the totals alongside a few representative comments.

It is built for small subscription businesses that cannot justify a customer research project but still want evidence.

What you get out of it

  • Churn reasons become numbers you can compare

    Instead of a feeling that people leave over price, you see that 14 of 40 cancellations cited price and 9 cited a missing integration. Ranked categories turn a vague worry into something you can prioritize.

  • Roadmap debates rest on evidence

    When the loudest customer is not the most typical one, a monthly breakdown settles the argument. You can show the team the share of churn tied to a specific feature gap before committing engineering time to it.

  • Pricing changes get tested against real feedback

    After a price increase, a rise in the price category is visible within a month. That tells you early whether the change is costing you customers, while there is still time to adjust.

  • Nobody reads hundreds of comments by hand

    The AI step tags each reason as it comes in, so the work that used to take an afternoon every quarter is finished before you sit down. Your time goes to acting on the pattern.

  • A consistent record across months

    Counters persist from one month to the next, so you can see whether a fix actually reduced a category. A support improvement that cuts churn from poor service shows up as a falling number rather than a hunch.

How it works

What happens, step by step

  1. Each time a customer cancels in Stripe, ClickRuntime reads the feedback they left.

  2. AI sorts the feedback into a reason, such as price, switched tool or missing feature.

  3. It keeps a running count for each reason.

  4. Once a month you get an email with the breakdown of reasons.

Before it runs live

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

What you get

RunsCollects as they arrive, acts daily
Find out why customers canceltoday, 9:00Succeeded
Email · Cancellation reasons up to Oct 01 7 price 4 switched tool 2 missing feature

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 Stripe 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.
ai_churn_reason_classification.pyexample
from datetime import date
from clickruntime import on_event, on_trigger, ai, state, notify, verify, credentials

REASONS = ["price", "missing feature", "switched tool", "not using it", "support", "other"]

@on_event
def handle(event):
    if not verify.stripe(event.body, event.header("Stripe-Signature"), credentials.secret("STRIPE_WEBHOOK_SECRET")):
        return {"ignored": "bad signature"}
    if event.json["type"] != "customer.subscription.deleted":
        return {"ignored": event.json["type"]}
    details = event.json["data"]["object"].get("cancellation_details") or {}
    text = f"feedback: {details.get('feedback')}; comment: {(details.get('comment') or '')[:1000]}"
    label = ai.generate(text, max_output_tokens=10,
                        system=f"Pick one cancellation reason from: {', '.join(REASONS)}. Answer with the reason only.").text.strip().lower()
    label = label if label in REASONS else "other"
    counts = state.get("counts") or {}
    counts[label] = counts.get(label, 0) + 1
    state.set("counts", counts)
    return {"reason": label}

@on_trigger
def monthly(event):
    counts = state.get("counts") or {}
    lines = [f"{n:>3}  {r}" for r, n in sorted(counts.items(), key=lambda x: -x[1])]
    notify.email_me(f"Cancellation reasons up to {date.today():%b %d}", "\n".join(lines) or "No cancellations.")
    state.set("counts", {})
    return counts

FAQ

Common questions

Which Stripe fields does it read?
It reads cancellation_details on the subscription, which includes the reason code Stripe collects from the customer portal and any free-text comment. If customers cancel without leaving a reason, those are counted as uncategorized rather than guessed at.
Can I define my own churn categories?
Yes. The category list is part of the instruction given to the AI step, so you can name them to match how your team talks, for example onboarding, bug, price and seasonal. Your assistant shows the updated list for approval first.
Does the AI see customer names or card details?
Only the cancellation reason and comment text are sent to the classification step. Card details are never part of that data, and keys for your Stripe account are stored as secrets, not in the instructions.
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 each time it checks. Checks that find nothing new and stop right away aren't counted.
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 “Find out why customers cancel” from your assistant

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