Automatically create JIRA issues from Outlook email support requests

Scheduled poll of Outlook shared inbox → AI triage → auto-create JIRA issues with labels and priority

Who

Teams who need to turn Outlook shared-inbox support emails into tracked JIRA issues

You get

Hourly fetch of new emails, deduplication, AI-generated labels/priority/summary/description, then JIRA creation

You need

n8n · jira · outlook

Steps

1. Configure trigger and email fetch

   Create a new n8n workflow. Add a Schedule Trigger node set to run every hour. Add a Microsoft Outlook node, choose Get Recent Messages, and configure the shared mailbox credential. In filtersUI, set receivedAfter to `={{ $now.minus({ "hour": 1 }).toISO() }}` to pull only the last hour. Keep fields such as body, from, subject, and receivedDateTime.

2. Deduplicate and convert format

   Add a Remove Duplicates node (named Mark as Seen in the template), select removeItemsSeenInPreviousExecutions, and set dedupeValue to `={{ $json.id }}` so each email is processed once. Then add a Markdown node with html set to `={{ $json.body.content }}` to convert HTML email bodies to Markdown for easier parsing.

3. AI triage and issue generation

   Add a Basic LLM Chain node (Generate Issue From Support Request), connect an OpenAI Chat Model sub-node (model: gpt-4o-mini) and a Structured Output Parser sub-node. In the LLM Chain text field, enter the user message template; in messages, enter the system prompt that instructs the AI to classify by label, assign priority 1–5, and rewrite summary and description. The Structured Output Parser schema must define labels (array of strings), priority (number), summary (string), and description (string).

   Execution prompt · Source text。Basic LLM Chain node messages.messageValues[0].message field

   Copy prompt

   =Your are JIRA triage assistant who's task is to
   1) classify and label the given issue.
   2) Prioritise the given issue.
   3) Rewrite the issue summary and description.
   
   ## Labels
   Use one or more. Use words wrapped in "[]" (square brackets):
   * Technical
   * Account
   * Access
   * Billing
   * Product
   * Training
   * Feedback
   * Complaints
   * Security
   * Privacy
   
   ## Priority
   * 1 - highest
   * 2 - high
   * 3 - medium
   * 4 - low
   * 5 - lowest
   
   ## Write Summary and Description
   * Remove emotional and anedotal phrases or information
   * Keep to the facts of the matter
   * Highlight what was attempted and is/was failing

   Execution prompt · Source text。Basic LLM Chain node text field

   Copy prompt

   =Reported by {{ $json.from.emailAddress.name }} <{{ $json.from.emailAddress.address }}>
   Reported at: {{ $now.toISO() }}
   Summary: {{ $json.subject }}
   Description:
   {{ $json.data.replaceAll('\n', ' ') }}

4. Create JIRA issue

   Add a JIRA node, choose Create Issue, and configure the jiraSoftwareCloudApi credential. Enter actual project and issue type IDs (the template shows 10000 as an example and it must be replaced). Set Summary to `={{ $json.output.summary }}`, Description to `={{ $json.output.description }}`, Labels to `={{ $json.output.labels }}`, and Priority to `={{ $json.output.priority }}`. Save and activate the workflow.

You are setting up an n8n workflow that fetches support emails from an Outlook shared inbox, triages them with AI, and creates JIRA issues. First confirm you have: an n8n instance, access to an Outlook shared inbox, an OpenAI API key, and a JIRA Cloud project. If you need to change the label set or priority definitions, edit the system prompt in the Basic LLM Chain node.