We just wrapped a Scale and optimize your service desk with AI agents session! In this session, we explored several different AI agent templates found in the space settings of a Jira Service Management space. These agents can help you reduce the amount of time manually managing your service desk, from making sure your knowledge base is up-to-date to assigning the right request type to a ticket.
Here’s a recap of the session, plus some extra resources to help get you started with these agents. Bookmark this page, test the agents in your service space, and join the discussion to share how you’re using these specialized agents to support and automate your team’s work!
Did you attend the session? Let us know what you thought by completing this quick, anonymous survey!
AI agent templates
In this session, we explored several different AI agent templates found in the space settings of a Jira Service Management space:
- Request Type Enricher: Reviews the ticket and recommends the correct request type.
- Re-opened Ticket Checker: When a resolved ticket is re-opened, the agent will see if it’s a genuine follow-up or just a “thank you!”
- Escalation Handoff Notes: Writes clear escalation handoff notes from the full ticket history.
- Knowledge curator: Turns recently resolved work into draft articles and identifies stale or outdated pages.
To find the AI agent templates, go to Space settings in your Jira Service Management space. Select AI agents from the sidebar, then select Templates.
All of these agent templates can be used as-is right away, but they can also be customized to fit the needs of your service desk. For example, you might want to add a specific tool or skill to the agent to give it access to more data and actions. Or, you might want to adjust the depth of the agent’s reasoning.
- Manually: The agents can be manually invoked on each ticket. This is a great solution if you want more control over when the agents act.
- Automatically: You can also create automation flows that automatically invoke the agent after a specific trigger. For example, if a ticket is reopened when a customer says thank you, you can create an automation flow that reviews the reopened ticket and automatically closes it if it’s not a genuine follow-up.
Try out an agent
Pick one of the agent templates to try in your space. When it opens in Rovo Studio, skim the instructions to get a sense of how the agent operates before hitting Publish. Start by manually invoking the agent on a few tickets before creating an automation.
Bonus: If you’re using the Request Type Enricher agent, try adding the Request Type Matcher Guidelines to your knowledge base. (Fill it in with your space-specific details, of course.)
🌟 Share a comment below with your own before-and-after experience. Did the agent template work correctly? Did you customize anything, like the instructions, tools, or skills? Have you automated the agent in any way, and if so, how?
Keep learning
