On a schedule

Review stale Jira tickets every week in Slack

Every Monday Slack lists Jira tickets that have not moved in 30 days, with a suggestion for each: close it, chase it or keep it.

Runs: On a schedule
Apps: Jira, Slack
AI: Yes, uses the built-in AI allowance
Access: Jira read (+comment); Slack chat:write

Send this to your assistant

Create a ClickRuntime automation: every Monday, find tickets in ENG not updated for 30 days and not done, have AI suggest close, chase or keep for each, and post the list to #eng.

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 team's Jira backlog has grown to hundreds of tickets, many of them untouched for months. Nobody trusts the board any more, planning takes longer, and real priorities get lost among old ideas.

A weekly list of stale tickets with a suggested action for each makes the clean-up a short, regular habit. The backlog shrinks to work the team actually intends to do, and the board becomes useful again.

What you get out of it

A backlog you can trust
Regular pruning keeps the list to work that matters. Planning becomes faster and clearer.
A suggestion for each ticket
AI proposes close, chase or keep with a short reason. Decisions take seconds instead of rereading each ticket.
Small and regular
A weekly review covers a manageable list. It never grows into a dreaded spring clean.
Forgotten work resurfaces
Tickets that matter but slipped are flagged to chase. Important work does not silently stall.

How it works

What happens, step by step

Every Monday, ClickRuntime finds tickets in your Jira project that have not been updated for 30 days and are not done.
AI reads each ticket's title, status and age and suggests whether to close it, chase it or keep it.
The list is posted to your #eng Slack channel with links and suggestions.

Before it runs live

Connect Jira
Connect Slack, then invite the app to the channel (type /invite @ClickRuntime there)

What you get

RunsOn a schedule

Review stale Jira tickets every week in Slacktoday, 9:00Succeeded

Slack · #engWeekly stale ticket review (12 tickets) 🗑️ ENG-120 close: replaced by the new export screen 📣 ENG-207 chase: customer Northwind still waiting

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 Google Sheets
Combine it with other Jira and Slack 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_stale_ticket_review_posted_to_slack.pyexample

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

JIRA, SITE = "https://api.atlassian.com/ex/jira/your-cloud-id", "https://acme.atlassian.net/browse/"
adf = lambda text: {"type": "doc", "version": 1, "content": [{"type": "paragraph", "content": [{"type": "text", "text": text}]}]}

def jira(method, path, **kw):
    resp = http.request(method, JIRA + path, headers={"Authorization": f"Bearer {credentials.connection('jira', 'work')}", "Accept": "application/json"}, **kw)
    return resp.raise_for_status() or (resp.json() if resp.content else None)

SCHEMA = {"type": "object", "properties": {"items": {"type": "array", "items": {"type": "object", "properties": {
    "key": {"type": "string"}, "action": {"type": "string", "enum": ["close", "chase", "keep"]}, "reason": {"type": "string"}}}}}}

@on_trigger
def run(event):
    tickets = jira("POST", "/rest/api/3/search/jql", json={"jql": "project = ENG AND updated <= -30d AND statusCategory != Done ORDER BY updated ASC",
                   "fields": ["summary", "status", "assignee", "updated"], "maxResults": 30})["issues"]
    if not tickets:
        return {"stale": 0}
    lines = "\n".join(f"{t['key']} [{t['fields']['status']['name']}] last updated {t['fields']['updated'][:10]}, "
                      f"assignee {(t['fields']['assignee'] or {}).get('displayName', 'none')}: {t['fields']['summary']}" for t in tickets)
    review = ai.generate(lines, json_schema=SCHEMA, max_output_tokens=1500,
                         system="For each stale ticket, suggest close, chase or keep, with a reason of up to 10 words.").json["items"]
    icon = {"close": "🗑️", "chase": "📣", "keep": "📌"}
    text = "\n".join(f"{icon[r['action']]} <{SITE}{r['key']}|{r['key']}> {r['action']}: {r['reason']}" for r in review)
    notify.slack(f"Weekly stale ticket review ({len(tickets)} tickets)\n{text}", channel="#eng")
    return {"stale": len(tickets)}

FAQ

Common questions

Does it close tickets itself?

No. It suggests an action. Your team decides and makes the change in Jira. It can optionally add a comment on each ticket asking the assignee for an update.

Can I change what counts as stale?

Yes. Choose the number of days, and exclude statuses or labels such as Backlog or someday.

How many tickets does it list?

Up to 30 each week, oldest first, so the review stays short. The rest appear in later weeks.

What permissions does it need?

Jira read (+comment); Slack chat:write. 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