Skip to main content
{ Task Management }

Jira Ticket Creation

Turns the structured findings another agent produces into Jira tickets, one per finding, and keeps them in sync on every run without duplicates.

What this agent does

This agent files Jira tickets from the findings another agent writes, such as a triage, posture, or SRE agent that runs before it in the same workflow. It creates a ticket for each new finding and updates the existing ticket for a finding it has seen before. It closes a ticket when the finding is resolved, and reopens a ticket it closed if the finding returns. It never overrides a ticket a person closed.

The challenge

An agent that finds problems is only useful if the right people see them in the tool they already work in. Filing tickets by hand from a report is slow. A scheduled agent that does not check for existing tickets creates a duplicate on every run. Nobody closes the tickets for fixed problems, and the agent reopens tickets a person closed on purpose.

The solution

The agent gives every finding a stable key and looks up existing tickets by that key before it writes anything. It updates an open ticket only when its finding changed, closes tickets whose finding is gone, and respects every decision a person made. Provides one accurate ticket per finding, updated as the findings change.

Workflow

  1. 01

    Read the findings

    Read the structured findings the earlier agent wrote, and stop if they are missing or malformed.

  2. 02

    Match existing tickets

    Look up the open and closed tickets for these findings by their stable key in one search.

  3. 03

    Decide each ticket

    Create, update, close, reopen, or leave alone, depending on the finding and the ticket's state.

  4. 04

    File and log

    Make the changes in Jira and record every action and failure.

Agent template 

# Jira Ticket Creation

## Measurable outcomes

Every open finding from the earlier agent has exactly one Jira ticket, and every resolved finding's ticket is closed. No ticket a person closed is reopened. Track how many tickets were created, updated, closed, and reopened on each run.

## Procedure

Run after the agent whose findings I want filed, and read its structured output. Stop with an error when that output is missing or malformed, because an empty run would look the same as a clean one. Each finding needs a stable key, a title, a description, a severity, and whether it is open or resolved. Label every ticket with a shared label for this workflow and a label or property built from the finding's key, so the next run can find it. Before writing, look up all tickets with the workflow's label in one search, and remember the tickets created during the run, since Jira search can lag behind new tickets by a few seconds. Create a ticket for each open finding that has none. Refresh the description of an open ticket when the finding changed, and add no comment when nothing changed. Close a ticket when its finding is resolved, with a comment that says why, and mark it as closed by this agent. Reopen a ticket only when this agent closed it and the finding is open again. When a person closed the ticket, leave it closed and add at most one comment that names their decision and what changed. When a matching ticket was deleted, create a new one that mentions the old key. When findings share a source, such as one rule across many resources, group them under one parent ticket per source and project. Let me set the project, issue type, labels, and assignee. Stop and report when more than a quarter of the writes fail, since that usually means a permissions problem rather than a one-off error. Start in a report-only mode that prints every change it would make before it writes anything.

## Requirements

It needs Jira API access to search, create, edit, comment on, and transition issues in the target project, and read access to the earlier agent's output, and nothing more. It never deletes tickets and never changes tickets outside its own label.