AI detection

Some situations cannot be captured with status fields or keywords: an unhappy customer, a hidden requirement, a team that is stuck. AI detection covers exactly these cases with a condition in plain language:

“A customer expresses dissatisfaction or threatens to escalate”

“Someone proposes a new requirement”

“The team is blocked and needs a decision”

The AI evaluates every new comment in scope and sends a notification on a match. AI detection is available as a trigger on ticket reminders (one ticket) and on filter alerts (all tickets in a filter).

Writing good conditions

Describe the meaning, not a word list. The AI also understands indirect statements: “this is getting annoying” counts as dissatisfaction even though the word “complaint” never appears. For exact words, the keyword filter on the comment trigger is the better and cost-free choice.

Conditions can be up to 500 characters long.

Traceability

Every AI decision, match or no match, is written to the reminder’s audit log together with a short reasoning. The log sits right below the reminder, behind Show log, in the panel on the ticket as well as on the overview page. An AI entry reads “AI found a match” or “AI found no match”, with the ticket, the time and the reasoning of the model including the model name. The question “why did this trigger” or “why did this stay quiet” now has an answer and a place to read it.

Monthly AI Credits

Each Jira site has a shared monthly pool of AI Credits. The current usage is visible at the top of the HeadsUp overview page.

• The pool depends on the number of licensed Jira users and the edition: 20 AI Credits per user per month in Standard, 200 in Advanced. Small sites get a guaranteed minimum of 100 and 500.
• All users share the pool freely; there is no per-user limit.
• When the pool is used up, AI reminders pause until the first of the next month. Anyone whose AI reminder wants to fire after that is notified once per month, always in the inbox and additionally by email. Anyone with no AI reminder coming up for the rest of the month is not notified. All other reminders keep working normally.

Good to know

• Evaluation runs on Atlassian-hosted AI models via the Forge platform. Comment texts never leave the Atlassian platform and are not shared with any third-party AI provider.
• AI is not a 100 percent guarantee. In unclear cases HeadsUp rather stays quiet than raises false alarms.
• The notification can arrive a few seconds later than with regular triggers, because evaluation runs asynchronously.
• Comments shorter than 15 characters are never evaluated. That keeps “ok” and “+1” away from the AI, and it also catches short comments that do carry meaning, such as “please escalate”.
• Comments written by apps and automations are never evaluated either. On a support queue a large share of comments is machine-written; they consume no AI Credits, while the regular triggers keep reacting to them.