What problem does it solve? Coordinating incident response across on-call rotations, paging, escalation policies, and incident tracking requires juggling multiple Datadog APIs and UIs, which slows down response during outages. ## Core Features & Use Cases - On-Call Management: Create and update on-call schedules, escalation policies, team routing rules, and notification channels (SMS, phone, email, Slack). - Paging & Escalation: Send high or low urgency pages to teams or users, then acknowledge, escalate, or resolve them. - Incident Tracking: List and filter incidents by state or severity, and retrieve full incident details. - Use Case: During a production outage, page the platform team, check who is on-call, track the active incident, and open a tracking case via the delegated case-management agent. ## Quick Start Ask the agent who is currently on-call for your team and to page them about the production database issue.