alerting-context

To retrieve PagerDuty incident context, you can request current on-call assignments, recent incident history, and alert patterns for a specific escalation policy or service. This centralizes triage data to speed up decision-making during active incidents.

Yes, you can pull MTTR metrics from PagerDuty. The Skill fetches mean, median, p95, min, and max MTTR values, allowing you to gauge incident response performance and identify trends in alert resolution times.

You need an escalation policy or service identifier to review recent incidents. The Skill then lists recent incidents, acknowledgements, and assignments to help you understand alert patterns and incident trends.

Yes, the tool relies on a credential-proxy API layer to securely fetch on-call data, incidents, and MTTR metrics. It uses Python scripts to interact with this API layer for data retrieval.

The best way to get current on-call rosters and recent incidents is to query the escalation policy directly. You can request the on-call roster and simultaneously review recent incidents to accelerate triage and context gathering.

Gathering PagerDuty context slows triage because responders must manually navigate multiple interfaces to find on-call assignments, incident history, and alert patterns. Centralizing this data reduces delays and speeds up decision-making.