AI Active Case Agent
Helping teams spot risky cases earlier
A predictive risk score built from signals support leads already watch, with alert rules that respect CRM status, working hours and repeat noise.
The problem
Support leads often learn a case is in trouble when the customer escalates. The goal was to flag rising risk while the team still had time to act.
My role
I defined the signals behind the risk score and how the agent behaves when it raises an alert.
The signals I defined
| Signal | What it adds to risk |
|---|---|
| Sentiment | Frustration that builds across messages, not a single sharp reply. |
| Severity | Business impact the customer or agent has set on the case. |
| Complexity | Cases that need several teams, products or handoffs. |
| Response SLA | Time left before the next response is due. |
| Resolution SLA | Time left before the resolution target is missed. |
| Account tier | The contractual and commercial weight of the account. |
| Case age | How long the case has been open relative to similar cases. |
Alert behavior
Different CRM statuses
Status changes what risk means. A case waiting on the customer should not build risk the way a case waiting on us does, and closed or resolved cases leave scoring.
Time when the team can act
Alerts arrive when the support team can respond. A risk raised outside their working hours is held for the start of their coverage instead of paging no one.
Cooling-off for repeat alerts
After an alert, the same case stays quiet for a cooling-off period unless its risk rises further, so leads see new problems instead of the same one again.
Signal levels
- Sentimenthigh
- Severityhigh
- Complexitymedium
- Response SLAmedium
- Resolution SLAhigh
- Account tierhigh
- Case agelow
How the agent behaved
- Tue 22:40Risk crosses alert thresholdHeld: outside team hours
- Wed 09:00Alert sent to support leadTeam coverage starts
- Wed 11:30Risk unchangedSuppressed: cooling-off
- Wed 15:10Sentiment drops, resolution SLA nearRe-alert: risk rose
- Thu 10:00Status set to Waiting on customerResponse clock paused
Metrics and outcomes I set
- Risk alerts acted on by support leads
- Alerts raised while there is still time before an SLA is missed
- Repeat alerts that add noise
Alerts that arrive early enough to act on and rarely enough to trust.
