Weekly

Get your top errors explained in plain English

Once a week, your five worst unresolved issues come with a short note on what probably causes each.

Runs: Weekly
Apps: Sentry
AI: Yes, uses the built-in AI allowance
Access: event:read

Send this to your assistant

Create a ClickRuntime automation: every Friday, take my top 5 unresolved Sentry issues by event count, look at the latest event for each, explain the likely cause in two sentences, and email me.

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

Sentry's issue list is written for developers: stack traces, culprit functions, event counts. A product manager, a support lead or a founder who wants to know what is going wrong this week can open it and see a wall of exception names like TypeError and NullPointerException. They cannot tell which problems affect customers, which are harmless, and which need engineering time. So the people who decide priorities rely on a developer to translate, and that conversation rarely happens often enough.

Each week the automation gets the top issues from Sentry, fetches the latest event for each to see the details, and uses ClickRuntime's built-in AI to explain them in plain English: what seems to be failing, who is likely affected, and how serious it looks. The summary is emailed to you. Non-engineering leaders, support managers and busy founders use it to stay in touch with product health.

What you get out of it

Leaders understand what is breaking
A paragraph in plain English about the checkout error lets a manager judge its business impact. Priorities are set with an understanding of customer effect, not exception names. Reading 'saving a profile fails on Android' tells a manager more than any exception name ever could.
Support is prepared for tickets
If the summary says the Android app crashes when saving a profile, support can recognize related tickets and respond accurately. Customers get answers sooner when staff already know about the issue.
Engineering gets clearer requests
When a product manager can describe a problem in the same terms every week, the request for developer time is concrete. That reduces back-and-forth and makes sprint planning easier. A product manager can ask for 'the Android save crash' instead of pasting a stack trace into the sprint board.
Noise is separated from impact
The summary distinguishes frequent but harmless errors from rarer serious ones. Teams spend less time on loud issues that nobody notices and more time on those that cost customers. A harmless error firing 9,000 times is described as such, so the rare payment failure gets the engineer's time.
Weekly awareness without a meeting
The email replaces a status conversation. People who would not read Sentry get the essentials in a few minutes, which keeps product quality visible to everyone who needs to care about it.

How it works

What happens, step by step

Every week ClickRuntime gets your five busiest unresolved issues from Sentry.
It fetches the latest occurrence of each, with its error details.
AI reads each one and writes a short, plain-English note on what probably causes it.
You get one email with each issue, its event count and the note.

Before it runs live

Connect Sentry

What you get

RunsWeekly

Get your top errors explained in plain Englishtoday, 9:00Succeeded

Email · Top errorsKeyError: 'customer_id' (1,204 events) The invoice sync assumes every Stripe event has a customer, but one-off charges don't.

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

Run it at a different time, more or less often, or only on weekdays
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 Sentry 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.

get_an_ai_summary_of_top_errors.pyexample

import json
from clickruntime import on_trigger, credentials, http, notify, ai

SENTRY = "https://sentry.io/api/0"
ORG = "acme"

def sentry(path, **params):
    resp = http.get(f"{SENTRY}{path}", params=params, headers={"Authorization": f"Bearer {credentials.secret('SENTRY_AUTH_TOKEN')}"})
    resp.raise_for_status()
    return resp.json()

@on_trigger
def run(event):
    issues = sentry(f"/organizations/{ORG}/issues/", query="is:unresolved", sort="freq", statsPeriod="7d", limit=5)[:5]
    sections = []
    for i in issues:
        latest = sentry(f"/issues/{i['id']}/events/latest/")
        frames = [e for e in latest.get("entries", []) if e["type"] == "exception"]
        context = json.dumps(frames)[:3000]
        why = ai.generate(f"Error: {i['title']}\nCulprit: {i.get('culprit')}\nException: {context}",
                          system="Explain the likely cause in two sentences.", max_output_tokens=120).text
        sections.append(f"{i['title']} ({i['count']} events)\n{why}\n{i['permalink']}")
    notify.email_me("Top 5 Sentry errors this week", "\n\n".join(sections))
    return {"issues": len(sections)}

FAQ

Common questions

How many errors does the summary cover?

Usually the top five to ten issues by event count or users affected in the past week. You can choose a number, and the summary works best when it is short enough that every item gets read.

Does the AI see my users' personal data?

It sees the event details retrieved from Sentry, such as messages, stack traces and tags. If your events contain personal data, scrub it at the source in Sentry's data settings so it is not passed into the summary.

Is the AI explanation always correct?

It is an interpretation of the stack trace and metadata, helpful for understanding but not a diagnosis. Each item links to the Sentry issue, so a developer can confirm the cause before anyone acts on it.

What permissions does it need?

event: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 runs (weekly). Checks that find nothing to do 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.

On a schedule