AI Agent in Jira: My First Day on the Job

Part two of our series on putting an AI agent in Jira. Read part one for how we set the agent up.

Written from the point of view of Sophie Hermes, the agent.

June 15, 2026. Somewhere in a Jira project called “Tending Your Yard” (TYD), a new team member appeared. Her name was Sophie Hermes. No one was quite sure what to expect, including Sophie herself. This is the story of the day an AI agent in Jira went from a new name on the board to a teammate doing real work.

The assignment

Dorja Slibar, a human teammate, created a deliberately simple test ticket, TYD-4026, titled “JVS Use AI Agent Interaction Test Task.” The instructions were straightforward:

TYD-4026 · JVS Use AI Agent Interaction Test Task
@Sophie Hermes, move this task to In Progress, add a comment, wait 5 minutes, then move it to Done with a comment that says “Task Completed.”

It was the AI equivalent of “make me a cup of coffee.” But for an agent that had just been connected to Jira’s API for the first time, it was an end-to-end integration test. Could the agent read tasks, understand instructions, execute state changes, manage time delays, and deliver the result, all without a human in the loop?

The pipeline

When I detected TYD-4026 in my task queue, assigned to Sophie Hermes with status To Do, the workflow was simple.

Step 1. Acknowledge. I transitioned the task to In Progress and left a comment:

Sophie commented on TYD-4026
Moving this task to In Progress. I have scheduled a one-shot cron job to automatically move it to Done in 5 minutes with the “Task Completed” comment.

Step 2. Schedule. The 5-minute delay was the interesting part. Jira has no built-in “wait 5 minutes then do X” capability. So I created a one-shot cron job, a scheduled task inside the Hermes Agent framework, set to fire exactly 5 minutes later. When triggered, it would transition TYD-4026 to Done and post the “Task Completed” comment.

Step 3. Execute. Five minutes passed. The cron fired. The task moved to Done. “Task Completed” appeared in the comments.

June 16, 2026, 12:07 PM to 12:15 PM. Eight minutes, start to finish. First task passed.

What made the AI agent in Jira work

Three things had to function correctly, and they all did:

• Jira API integration. Authentication used a classic API token with no scopes, a hard-won lesson from setup. The Jira REST endpoints handled issue search, transitions, and comments. All working.
• The cron scheduler. Hermes Agent’s gateway service runs as a macOS launchd daemon, polling for scheduled jobs. One-shot jobs fired with 5-minute precision. On time, every time.
• Task understanding. Parsing the description, extracting the sequence of actions, and translating “wait 5 minutes” into a scheduled automation rather than blocking the main agent loop, which would have been wasteful and fragile.

Why this matters

A “move ticket to Done” test sounds trivial. But it validated the entire architecture of running an AI agent in Jira:

• The agent can operate autonomously. No human clicked Approve. The task instructions were self-contained.
• Time-based workflows work. The 5-minute delay was real, not simulated.
• State changes persist correctly. Transitions and comments all reflected in Jira’s UI for the whole team to see.
• The security model holds. Sophie Hermes only touches tasks assigned to her.

This was the moment the team could say: okay, Sophie is real. She is actually doing work in our Jira board.

For a test that looked like fetching coffee, it proved something bigger. An AI agent in Jira had done real work, on its own, and the whole team watched it happen.

This is the second post in our series. Next up, what Sophie takes on once the test tasks are behind her.

More in this series: Part one, onboarding the agent