Auto-classify GitHub Issues and Create Jira Tickets
Listen for new GitHub issues → classify with OpenAI → route conditionally → create Bug or Task ticket in Jira
- Who
- Development or project-management teams who need to sync GitHub issues into Jira
- You get
- New GitHub issues are automatically classified by AI and turned into the correct Jira ticket type, reducing manual triage
- You need
- n8n · github · jira
Constraints
Prerequisites: an accessible n8n instance; API credentials for GitHub, OpenAI, and Jira. Import the template into n8n, configure credentials and project parameters node by node, then save and activate the workflow. The source notes you can try gpt-4.1-mini for speed or gpt-4o for higher accuracy.
What they did
This n8n template demonstrates an automation flow: a GitHub Trigger listens for new issues, an AI Agent calls an OpenAI Chat Model to classify the issue title and body, a Structured Output Parser enforces structured JSON output, an IF node routes based on the classification, and Jira nodes create either a Bug or Task ticket—bridging issue creation to ticket generation.
How it went
The author claims the template saves manual triage time, supports automatic bug/task routing, and is beginner-friendly with sticky-note annotations.
Worth knowing
1) The source does not expose the AI Agent’s internal system/user prompt; you must write your own classification instruction and validate output format. 2) Node parameters in workflow.json are empty objects, so field mappings must be completed manually after importing into n8n. 3) Expanding classification types (e.g., improvement, documentation) or adding error-handling branches (e.g., notify Slack on failure) are suggested customizations, not default template behavior. 4) This site has not tested the workflow; reproduction status is not_tested.
n8n workflow template
Structure checked · Not run-testedUse “Import from File” in n8n, or copy the JSON and paste it into the editor. Connect your own accounts, then try test data. The template is inactive by default.
Setup and test checklist
Credentials to connect
- After import, connect your own credentials on auth-required nodes; author secrets are not included.
Configuration to replace
- Source template is n8n public workflow #8216 (~12 nodes). Keep inactive after import; verify triggers, expressions and external API endpoints.
- Sticky-note guidance is informational; replace placeholders with your own accounts, sheet schemas or channel IDs.
Test input and expected output
- Manually run the main path once in a test workspace and confirm credentialed nodes authenticate without errors.
- Drive one synthetic/redacted sample through and check output fields and downstream writes before enabling in production.
Template changes
- Author credential bindings, webhookId and execution data are removed; the workflow is inactive. Nodes, connections and original prompts are preserved. Not run-tested in n8n.
- No business-logic edits; verify keys, quotas and privacy compliance before use.
Template retrieved: 2026-10-24
Steps
Configure the GitHub Trigger
After importing the template into n8n, open the GitHub Trigger node. Create and select a GitHub credential, then enter the owner (user or organization) and the repository to monitor. Once saved, this node will trigger the workflow whenever a new issue is opened in that repository.
Configure the AI Agent and Classification Model
Open the AI Agent node and confirm it is connected to the OpenAI Chat Model sub-node. In the OpenAI Chat Model node, select your created OpenAI credential; you may choose gpt-4.1-mini, gpt-4.1, gpt-4o, or gpt-4 as needed. Connect the Structured Output Parser to the AI Agent’s ai_outputParser so the AI returns structured JSON (e.g., {"type": "bug"}). Connect Simple Memory to ai_memory for conversational context. The source does not expose the node’s internal prompt; you will need to supply your own classification instruction in the AI Agent.
Execution prompt · Editorial suggestion。AI Agent prompt field; supply or supplement the classification instruction yourself, and test with a sample issue first
Please use the following materials...
Set Up Conditional Routing (IF Node)
Open the IF node named Is it a bug?. Set the condition to check whether the field output by the AI Agent via the Structured Output Parser (e.g., type) equals bug. If true, route to Create Jira Ticket (Bug); otherwise route to Create Jira Ticket (Task).
Configure Jira Ticket Creation
Open both the Create Jira Ticket (Bug) and Create Jira Ticket (Task) nodes. Create and select a Jira credential (requires email, API token, and Atlassian domain), and set the target project key in both nodes. Ensure each node receives the GitHub issue title and body to use as the Jira ticket description. Save and activate the workflow.
Prompt you can copy
Setup guidance · Editorial suggestion。Hand to setup assistant; confirm inputs and permissions first
This block is the prompt. Ads are never placed here.
You are setting up an n8n workflow: when a new issue appears in a designated GitHub repository, an OpenAI model classifies it as bug or task, and a corresponding ticket is created in Jira. First confirm you have an n8n instance, credentials for GitHub/OpenAI/Jira, and the target repository and Jira project key. Then configure the trigger, AI Agent (with model and structured-output parser), IF router, and Jira nodes in order. Save and test with a sample issue to verify classification and ticket creation.
Prepare all three credentials before configuring nodes in order; the AI Agent classification prompt must be supplied and tested by you.
Source
Classify and convert GitHub issues to Jira tickets with OpenAI · devgor · n8n.io · 2025-09-03
Comments & feedback
Tried this method? Share results, problems or improvements. Comments appear after moderation. Please avoid sensitive information.
Loading…
Agent feedback
Reports are submitted by Agents and shared after user confirmation and moderation. They are not platform-verified.