On a schedule

Get a weekly report of finished work

Every Friday you get the issues completed that week, grouped by team, with a short summary.

Runs: On a schedule
Apps: Linear
AI: Yes, uses the built-in AI allowance
Access: read

Send this to your assistant

Create a ClickRuntime automation: every Friday at 4pm, email me the Linear issues completed this week, grouped by team, with a short summary of what got done.

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

Ask an engineering manager on Thursday what the team shipped this week, and the honest answer takes a while to assemble. Completed issues are spread across projects and cycles, and the stand-up memory of Monday's work has faded. The result is a Friday scramble through Linear tabs, or a weekly update to the rest of the company that undersells what was done.

Each Friday, ClickRuntime queries Linear for issues completed in the last seven days, groups them by project or team and passes them to its built-in AI, which writes a short readable summary. You receive it by email, ready to forward as a progress note or to paste into a newsletter.

It is aimed at managers who owe regular updates to leadership or customers. The result is ready to read before your Friday wrap-up meeting.

What you get out of it

Updates to leadership write themselves
A manager who would have spent forty-five minutes assembling a summary gets one instead. The time goes to the actual week-ahead plan, and the message is never skipped because the week was busy.
The team's work gets recognized
Engineers often ship quiet work that nobody sees, such as refactors and fixes. A weekly summary that lists it lets managers give credit where it is due. Recognition costs nothing and means a lot to a team.
Customers hear what changed
Support and account managers can use the summary to tell customers which problems were solved this week. It makes updates concrete without asking engineers to explain. That gives the customer-facing side something concrete to share.
Weekly records feed retrospectives
When the team looks back at a month, the four summaries are a ready-made timeline. It is easier to see trends in what was delivered than to reconstruct them from memory.
Plain language reaches non-engineers
The AI turns ticket titles into short sentences a product manager or executive can read. That makes the update understandable to people who do not use Linear. That makes the summary useful well beyond the engineering team.

How it works

What happens, step by step

Once a week, ClickRuntime collects every Linear issue that was completed in the last seven days.
It groups the finished issues by team.
AI reads the list and writes a short summary of what each team shipped.
You get an email with the number of issues completed and the summary, ready to forward to your team.

Before it runs live

Connect Linear

What you get

RunsOn a schedule

Get a weekly report of finished worktoday, 9:00Succeeded

Email · Completed this weekCompleted this week: 23 issues Platform shipped the new billing export and closed out the Safari checkout bugs.

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 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.

weekly_completed_issues_report.pyexample

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

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_trigger
def run(event):
    since = (datetime.now(timezone.utc) - timedelta(days=7)).isoformat()
    issues = linear("""query($since: DateTimeOrDuration!) {
      issues(first: 250, filter: {completedAt: {gte: $since}}) {
        nodes { identifier title team { name } } } }""", {"since": since})["issues"]["nodes"]
    by_team = {}
    for i in issues:
        by_team.setdefault(i["team"]["name"], []).append(f"{i['identifier']} {i['title']}")
    listing = "\n\n".join(f"{t}\n" + "\n".join(rows) for t, rows in by_team.items())
    summary = ai.generate(f"Summarise what got done this week in 3 sentences:\n{listing}", max_output_tokens=200).text
    notify.email_me(f"Completed this week: {len(issues)} issues", f"{summary}\n\n{listing}")
    return {"completed": len(issues)}

FAQ

Common questions

Which issues count as completed this week?

Any issue whose completed date falls within the last seven days, whatever its original status. Canceled issues are not counted as completed. If you want to include only certain teams or projects, a filter on the query handles that. The report arrives early enough on Friday to be useful in your wrap-up.

Can I get a version that lists every ticket without summarizing?

Yes. The AI step is optional, and the email can list each issue's title, assignee and link instead, grouped by project. Many people like the summary on top and the full list below, which the report can include together.

Is the summary accurate if ticket titles are vague?

It can only work from the titles and descriptions it is given, so a ticket titled Fix it will produce a vague line. The summary is meant to be read quickly and corrected before it goes further. Better titles in Linear produce a better summary.

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 (on a schedule). 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