How does AI Mention Triage classify @mentions?

Every @mention is classified automatically across three independent dimensions as soon as it’s posted. There’s nothing to configure — the AI handles it.

Action — what does this need from you?

Value	Meaning
Respond	A direct question or request needs a reply
Review	Feedback or review has been requested
Approve	Your sign-off is needed before work can proceed
Fix	Something is broken and needs correcting
Implement	A new feature or enhancement needs building
Monitor	An ongoing situation to keep an eye on — no action needed yet
Acknowledge	A completed event or notification — informational only

Urgency — how soon?

Value	Typical window
Critical	Active incident affecting all users
High	Time-sensitive, deadline within hours
Normal	Standard work item, no immediate deadline
Low	No deadline, can wait

Urgency badges include a short hint describing what’s at stake, so you don’t have to open the item to know why it’s marked the way it is.

Impact — who does this affect?

Value	Meaning
Customer	An external party — users, clients, patients, students
Revenue	A financial outcome — sales, billing, contracts
Team	An internal group or department
Individual	One person only

Note: Classification happens once, when the comment is first posted. If you edit a Confluence comment afterward, it’s reclassified automatically. Jira comment edits are not currently reclassified — if a Jira comment’s meaning changes significantly after editing, the original classification stays.

If classification doesn’t complete (for example, if the AI doesn’t respond in time), the item is marked as failed rather than left unclassified. You can trigger a retry by editing the comment again.