Skip to main content

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.

Coordinate across teams

Push high-ARR customer stories to CS; push queue-level backlog to ops; push product-correlated volume surges to engineering.

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.