Documentation Index
Fetch the complete documentation index at: https://docs.datagenie.ai/llms.txt
Use this file to discover all available pages before exploring further.
The problem
SLA dashboards tell you when a team missed a target. They rarely tell you early enough that a specific queue, priority level, or customer segment is about to breach — when the team could still course-correct.What DataGenie autonomously detects
Queue-level backlog anomalies
Unusual backlog growth by queue, priority, region, or customer segment — before aggregate SLA turns red.
First-response SLA drift
Median and p95 response-time anomalies across ticket categories — with Root KPI attribution.
Ticket-volume surges
Unusual inbound volume tied to product releases, outages, or pricing changes — connected to Business Events.
Customer-level risk signals
High-ARR customers with ticket-pattern anomalies — so CS and support coordinate.
How to operationalize it
Onboard the support dataset
GO ingests a sample of tickets and derives KPIs: volume, first-response, resolution time, backlog, by queue × priority × region.
Configure Multi Yhat baselines
Forecast-based for volume, reference-based for SLA — so anomalies are detected against the right baseline per KPI.
Alert on breach risk, not breach
Set up alerts on Top Stories ranked by impact — the team gets notified before the aggregate SLA turns red.
Relevant features
Multi Yhat
Compare multiple detection baselines per KPI.
Alerts
Route breach-risk stories to the right team.
Business Events
Document releases and outages so volume surges explain themselves.