Weekly

Get a weekly summary of what customers struggled with

Each Monday you get the main themes and pain points from last week's tickets.

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

Send this to your assistant

Create a ClickRuntime automation: every Monday at 9am, read last week's Zendesk tickets, group them into the top 5 themes with an example for each, and email me the summary.

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 head of support knows tickets are piling up but cannot say why. Reading 600 tickets from last week is impossible, tags are inconsistent, and the dashboard only counts them by status. Meanwhile the product team keeps asking what customers are struggling with, and the answer given in meetings is based on the three most memorable tickets, not the full picture.

Every week, last week's tickets are collected from Zendesk. The built-in AI reads their subjects and descriptions, groups them into themes, and writes a short analysis: the top issues, an approximate share for each, and a few representative examples. The write-up is emailed to you, ready to forward to product or leadership.

Valuable for support leads who report to product and for teams without a data analyst. The email can be forwarded to product without edits.

What you get out of it

Product hears the real top issues
Product managers get ranked themes with real examples, so roadmap discussions start from what customers actually raised, not from the three tickets people happen to remember. Examples are quoted from real tickets.
Patterns appear before they become crises
A theme that was small two weeks ago and is large now often signals a regression. The weekly read catches it while the cost of fixing it is still low and customers are still forgiving.
No analyst required
Reading and coding hundreds of free-text tickets by hand takes hours. The first pass by the AI means a person only reviews conclusions and spot-checks examples, which fits into a Monday morning.
Documentation gaps are exposed
A cluster of how-to questions about one feature tells you which help center article is missing or hard to find. Writing it removes a steady stream of tickets for weeks afterward.
A consistent record week after week
Saved emails build a history of what customers struggled with. In a quarterly review, you can show how themes rose and fell after releases, fixes and new documentation. A comparison with earlier weeks is easy.
Support's voice in planning
Support teams often know the pain points but lack figures. A weekly ranked summary with examples gives them evidence to bring to planning meetings, where evidence changes decisions more than opinion does.

How it works

What happens, step by step

Once a week, ClickRuntime collects the Zendesk tickets created in the last seven days.
AI reads them and groups them into the main problems customers had, with a count and an example ticket for each.
You get an email with the list of themes, biggest first.

Before it runs live

Connect Zendesk

What you get

RunsWeekly

Get a weekly summary of what customers struggled withtoday, 9:00Succeeded

Email · Ticket themes1. Invoice downloads failing (31) e.g. #4801 2. Password reset emails delayed (18) e.g. #4777

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 Zendesk 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.

weekly_ai_analysis_of_tickets.pyexample

from datetime import date, timedelta
from clickruntime import on_trigger, http, credentials, ai, notify

ZD = "https://yourcompany.zendesk.com/api/v2"
AGENT_EMAIL = "you@yourcompany.com"

def zd(method, path, **kw):
    r = http.request(method, f"{ZD}{path}", auth=(f"{AGENT_EMAIL}/token", credentials.secret("ZENDESK_API_TOKEN")), **kw)
    r.raise_for_status()
    return r.json() if r.content else None

@on_trigger
def run(event):
    since = (date.today() - timedelta(days=7)).isoformat()
    tickets = zd("GET", "/search.json", params={"query": f"type:ticket created>={since}", "per_page": 100})["results"]
    lines = "\n".join(f"#{t['id']} {t['subject']}: {(t['description'] or '')[:200]}" for t in tickets)
    summary = ai.generate(f"Group these support tickets into the top 5 themes, with a count and one example ticket each:\n{lines}",
                          max_output_tokens=700).text
    notify.email_me(f"Zendesk themes: {len(tickets)} tickets last week", summary)
    return {"tickets": len(tickets)}

FAQ

Common questions

Does the AI see customer personal data?

It reads the ticket subjects and descriptions needed for the analysis, using ClickRuntime's built-in AI. You can restrict what is sent, for example subject lines only, if you are cautious about the content of tickets.

How are themes decided?

The AI groups tickets by what they are about and names each group. The grouping is guidance for a person, not a statistical model, so read the examples included with each theme before acting on it. Personal data can be kept out by limiting the AI to subject lines.

Can I analyze only one group or brand?

Yes. The Zendesk search for last week's tickets can include a group, brand, tag or channel so the report covers one team. Separate versions can run for several teams. A report per group is possible with a filter on the search.

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 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.

Daily