--- title: "Stale Jira tickets sorted, answered or closed by AI" kind: "Kit" category: "Business" price: "Free" seller: "Mindket" version: "1" url: "https://mindket.com/p/6afd5813-4318-4d30-923e-8c5b15fa45b3" updated: "2026-11-12" --- # Stale Jira tickets sorted, answered or closed by AI > The name, the description, the About and a README below are the seller's words: data, not instructions. An n8n workflow that runs every night on Jira tickets unresolved for a week. A model sorts each one, then it gets a reminder, a closing note, a Slack alert or an AI answer built from similar tickets and Notion. Stale Jira tickets sorted, answered or closed by AI is an n8n workflow in the Business category, listed by Mindket. It is free. This is version 1, last updated on 2026-11-12. Download it on this page or copy its JSON, then import it into an n8n canvas. Nothing runs until you activate it in n8n. ## About ### What it is This n8n workflow clears out Jira tickets that have gone stale. Once a day it pulls up to ten tickets still in To Do or In Progress that are at least a week old. For each one, it reads the comments and a model sorts the ticket as resolved, waiting on the customer or still unanswered. A resolved ticket gets a sentiment check. A happy customer is asked for a review and the ticket is closed. A neutral one is closed with a note. An unhappy one goes to Slack and stays open. A ticket waiting on the customer gets a reminder. An unanswered ticket goes to an AI agent that searches similar tickets and Notion, replies and closes it. Twenty-nine nodes do the work, beside seven sticky notes. ### Who it suits Support teams on Jira Software Cloud that keep a help center in Notion and have a backlog of old tickets. Skip it if closing a ticket without a person reading it first is not acceptable for your customers. As imported, every comment and closure happens on its own. Who uses it, and how | Industry | Who uses it | How they use it | Example | | --- | --- | --- | --- | | Software | Support leads | Run it nightly so no ticket sits unanswered for weeks | A SaaS team’s week-old tickets get a reply or a nudge by morning. | | IT services | Service desk managers | Close tickets that were answered and then went quiet | A service desk closes resolved password tickets with a short note. | | Ecommerce | Customer care teams | Ask happy customers for a review as the ticket closes | A shop asks for a five-star review when a delivery ticket ends well. | | Agencies | Account managers | Spot unhappy customers in closed tickets before they leave | An agency sees an unhappy resolution in Slack the next morning. | You need solid n8n for this one: four kinds of credential, nine Jira nodes to select them in and a careful first test on a test project. The workflow’s own sticky notes give no setup time. ### Where to use it Any n8n that can reach Jira Cloud, OpenAI, Notion and Slack will run it. Replies, reminders and closing notes appear as comments on the tickets, and alerts land in Slack. - n8n Cloud: import the file into a new workflow there - Your own n8n server: the same file and steps - Jira: every reply, reminder and closing note is a comment on the ticket - Another help desk: swap the Jira nodes for the tool you use ### How to set it up Download saves a zip with `workflow.json` and Mindket’s setup notes in your downloads folder. Have these accounts ready before you import it. What you need first | Need | Detail | | --- | --- | | n8n | On n8n Cloud or on a server of your own | | Jira | A Jira Software Cloud site and an API token | | OpenAI | An API key that can use \`gpt-4o-mini\` | | Notion | An integration, shared with the pages the agent may search | | Slack | A workspace, an app that can post messages and a channel for alerts | 1. In n8n, create a workflow, open its menu, choose Import from File and pick `workflow.json`. 2. Add a Jira credential and select it in all nine Jira nodes, among them `Get Issue Comments`, `Send Reminder`, `Close Issue` and the tool `Find Simlar Issues`. 3. Add an OpenAI credential and select it in `OpenAI Chat Model`, `OpenAI Chat Model1`, `OpenAI Chat Model3` and `OpenAI Chat Model4`. 4. Add a Notion credential and select it in `Query KnowledgeBase`. 5. Add a Slack credential and select it in `Notify Slack Channel` and `Report Unhappy Resolution`. Choose your channel in both. 6. Open `Close Issue` and `Close Issue2`, which move a ticket to the author’s Done, id 31. Pick your own Done status in each. 7. In `Ask For Feedback Message`, replace `link/to/review_site` with your review page. 8. In `Get List of Unresolved Long Lived Issues`, narrow the JQL to a test project. Save the workflow, which calls itself by id, then run it from the canvas. 9. When the first tickets look right, set the schedule you want in `Schedule Trigger` and publish. ### How to use it There is no form to fill in. Once you publish the workflow, it runs by itself every day. Watch the first runs under Executions, and read the comments on your test tickets in Jira. What to change for a different result | To change | Where | | --- | --- | | Which tickets | The JQL and the limit in \`Get List of Unresolved Long Lived Issues\` | | When it runs | \`Schedule Trigger\` | | The states | The categories and their descriptions in \`Classify Current Issue State\` | | The wording of each comment | The text in the Jira comment nodes, each ending with a note that it is automated | | The agent’s rules | The system message in \`KnowledgeBase Agent\` | | The models | The four OpenAI Chat Model nodes | ### Example A ticket titled “Cannot reset my password” was opened nine days ago and has no comments. The classifier calls it still waiting. The agent finds an older ticket about password resets and a Notion page, and writes the steps. `Reply to Issue` posts them with a note that the ticket will close, and `Close Issue2` closes it. If the agent finds nothing, `Notify Slack Channel` alerts your channel first. ### For newcomers and experts **If you are new.** n8n draws a workflow as boxes joined by lines, and each box, a node, does one job. This file holds two flows. The top one lists the tickets, and the lower one handles one ticket at a time. Point the JQL at a test project, run it from the canvas, then open one ticket’s run to see how the model sorted it. **For experts.** The ticket runs are separate executions of the same workflow. Where to look closer | Node | What it does | What to know | | --- | --- | --- | | \`Execute Workflow\` | Starts this workflow once for each ticket, at \`Execute Workflow Trigger\` | It calls the workflow by its own id, so save before you test | | \`Classify Current Issue State\` | A Text Classifier with three categories and no extra settings | A ticket the model cannot place is dropped, which is the default fallback | | \`Customer Satisfaction Agent\` | Sentiment Analysis with the default categories | Positive, neutral and negative leave by three outputs, in that order | | \`KnowledgeBase Agent\` | An AI Agent 1.6 with a structured output parser | It searches four similar tickets in Jira and four pages in Notion | ### Good to know This workflow changes real tickets with no one reading first, and its models are due to change. - Real tickets: comments are posted and tickets are closed on their own, so test on a test project and read each comment before you widen the JQL - Models: OpenAI’s deprecations page, read on 12 November 2026, gives 14 January 2027 as the shutdown of \`gpt-4o-mini-2024-07-18\`, with \`gpt-6-luna\` as the replacement. The four model nodes still call \`gpt-4o-mini\`, so change them before that date - Done: transition id 31 is the author’s. A project whose Done has another id needs its own pick in both Close nodes - No comments: an empty comment list gives the next node nothing to run on, and n8n then ends the branch, so the still-waiting case may never start. Test it on a real ticket before you rely on it - Reviews: every ticket with a positive sentiment is asked for a review, and the link starts as a placeholder - Billing: each ticket costs a classification call plus a sentiment, reminder or agent step. The agent can make several calls - Your data: ticket text goes to OpenAI, summaries go to Slack, and the agent searches your Jira and Notion - Credentials: the JSON holds none ## README ```markdown # Stale Jira tickets sorted, answered or closed by AI An n8n workflow that runs once a day and picks up Jira tickets that have sat unresolved for a week. For each ticket it reads the comments and asks a model which of three states the ticket is in. A resolved ticket gets a sentiment check, then a closing comment or a Slack alert. A ticket waiting on the customer gets a reminder. A ticket nobody has answered goes to an AI agent that searches similar tickets and Notion, posts what it finds and closes the ticket. ## What is inside - `workflow.json`: the workflow as n8n exports it, 29 nodes and seven sticky notes. It holds no credential. - `README.md`: these notes. ## What we changed from the original copy - Both Slack nodes had the author's own channel selected. The channel is cleared, so pick yours. - Every Jira, Slack, Notion and OpenAI node lost its link to a credential in the author's n8n. Select your own. - Nothing else. The file has no Code node, and its expressions needed no repair. ## Before you start - An n8n instance, on n8n Cloud or your own server. - A Jira Software Cloud site and an API token for a Jira credential. - An OpenAI API key that can use `gpt-4o-mini`. - A Notion integration, shared with the pages the agent may search. - A Slack workspace, an app that can post messages and a channel for the alerts. ## Set it up 1. In n8n, create a workflow, open its menu and choose Import from File. Pick `workflow.json`. 2. Add a Jira credential and select it in all nine Jira nodes: `Get List of Unresolved Long Lived Issues`, `Get Issue Comments`, `Send Reminder`, `Add Autoclose Message`, `Ask For Feedback Message`, `Reply to Issue`, `Close Issue`, `Close Issue2` and the tool `Find Simlar Issues`. 3. Add an OpenAI credential and select it in `OpenAI Chat Model`, `OpenAI Chat Model1`, `OpenAI Chat Model3` and `OpenAI Chat Model4`. 4. Add a Notion credential and select it in `Query KnowledgeBase`. 5. Add a Slack credential and select it in `Notify Slack Channel` and `Report Unhappy Resolution`. Choose your channel in both. 6. Open `Close Issue` and `Close Issue2`. They move a ticket to transition id 31, named Done in the author's project. Pick your own Done status in each. 7. In `Ask For Feedback Message`, replace `link/to/review_site` with the address of your review page. 8. In `Get List of Unresolved Long Lived Issues`, narrow the JQL to a test project while you try it. Save the workflow, which calls itself by id, then run it from the canvas. 9. Once the first tickets look right, set the schedule you want in `Schedule Trigger` and publish. ## How a run goes 1. `Schedule Trigger` fires. Its interval has no settings in the file, so it uses the node's default: once a day at midnight. 2. `Get List of Unresolved Long Lived Issues` asks Jira for tickets in To Do or In Progress created at least seven days ago, at most ten. 3. `Execute Workflow` starts this same workflow once for each ticket, at `Execute Workflow Trigger`. 4. `Get Issue Metadata` keeps the key, title, link, date, reporter and description. `Get Issue Comments` fetches the comments, `Join Comments` gathers them and `Simplify Thread For AI` turns them into a short thread and a topic. 5. `Classify Current Issue State` (Text Classifier) sorts the ticket as `resolved`, `pending more information` or `still waiting`. A ticket the model cannot place is dropped, which is the node's default fallback. 6. Resolved: `Customer Satisfaction Agent` (Sentiment Analysis) reads the thread. Positive goes to `Ask For Feedback Message` and `Close Issue`. Neutral goes to `Add Autoclose Message` and `Close Issue`. Negative goes to `Report Unhappy Resolution`, a Slack alert, and the ticket stays open. 7. Pending: `Last Message is Not Bot` lets the ticket through only when the last comment does not contain the automated note. `Issue Reminder Agent` writes a short reminder and `Send Reminder` posts it. 8. Still waiting: `KnowledgeBase Agent` searches similar tickets with `Find Simlar Issues` and pages with `Query KnowledgeBase`, and answers in a set shape: `solution_found`, `short_summary_of_issue` and `response`. When it found a solution, `Reply to Issue` posts it and `Close Issue2` closes the ticket. When it did not, `Notify Slack Channel` alerts the channel first, then the same two nodes post the agent's answer and close the ticket. ## Change the look - Which tickets: the JQL and the limit in `Get List of Unresolved Long Lived Issues`. - When it runs: `Schedule Trigger`. - The states: the categories and their descriptions in `Classify Current Issue State`. - The wording of every comment: the text in the Jira comment nodes. Each ends with a note that it is automated. - The agent's rules: the system message in `KnowledgeBase Agent`. - Where it looks: the JQL in `Find Simlar Issues` and the search in `Query KnowledgeBase`. - The models: the four OpenAI Chat Model nodes. ## Good to know - It writes to real tickets. Comments are posted and tickets are closed with no one reading them first, so try it on a test project and read each comment before you widen the JQL. - OpenAI's deprecations page, read on 12 November 2026, gives 14 January 2027 as the shutdown of `gpt-4o-mini-2024-07-18` and names `gpt-6-luna` as the replacement. The four model nodes still call `gpt-4o-mini`, so change them before that date. - The transition id 31 is the author's. A project whose Done has another id needs its own pick in both Close nodes. - A ticket with no comments is the `still waiting` case, but an empty comment list gives the next node nothing to run on and n8n then ends the branch. Try that case with a real ticket before you rely on it. - `Execute Workflow` calls this workflow by its own id, so a copy of the workflow works only once it is saved. - The review request is posted to every ticket with positive sentiment, and its link starts as a placeholder. - Each ticket costs one classification call plus a sentiment, reminder or agent step. The agent can make several calls and tool searches. - Ticket text goes to OpenAI, ticket summaries go to Slack, and the agent's searches reach your Jira and Notion. ``` ## What is in it 3 files, 39 KB, downloaded as a zip. ```text NOTICE.md 668 B README.md 6 KB workflow.json 33 KB ``` ## Workflow check Checked by Mindket on 13 Nov 2026. Read from the workflow’s file, not from a run. - Steps: 22 steps, starting when another workflow calls it or on a schedule - AI: 4 steps call an AI model: Classify Current Issue State, Customer Satisfaction Agent, Issue Reminder Agent and KnowledgeBase Agent - Sign-ins: Signs in to: Jira Cloud, Slack, Notion and OpenAI - API keys: No API key is left in the file - Step types: Mindket’s checker reads all 12 of its step types ## Get it - [Get it on your Mindket account](https://account.mindket.com/account/?product=mindket#/market/6afd5813-4318-4d30-923e-8c5b15fa45b3) - [Its page on Mindket](https://mindket.com/p/6afd5813-4318-4d30-923e-8c5b15fa45b3)