Amazon Quick and New Relic launch AI agent for incident triage

Amazon Quick has unveiled an agentic incident triage assistant that coordinates investigation and handoff steps in a single conversational workflow, integrating New Relic's Model Context Protocol (MCP) Server and Asana via built-in connectors. The agent responds to prompts like "Checkout is slow… Generate RCA brief" by calling five New Relic reasoning tools in parallel: generate_alert_insights_report (identifies key alert drivers), generate_user_impact_report (quantifies blast radius in users and services), analyze_entity_logs (surfaces error signatures), analyze_transactions (finds slow or failing requests), and natural_language_to_nrql_query (converts plain English to New Relic Query Language and runs it against observability data). It then assembles a root cause analysis brief with evidence links and automatically creates a tracked Asana task in a designated "SRE Incident Triage" project.

For engineering leaders, reducing mean time to resolution (MTTR) is a direct business driver. In internal testing using New Relic's own applications, the agent significantly reduced the evidence-gathering phase of incident triage, leading to faster resolution and lower risk of knowledge loss between engineering shifts. The pattern demonstrates a broader capability in Amazon Quick: connecting enterprise tools to AI agents through native action connectors. Prerequisites include an Amazon Quick Professional subscription, a New Relic account, and an Asana workspace with an SRE Incident Triage project. The setup walks through New Relic and Asana integrations in the Amazon Quick Integrations console, then creating a chat agent that orchestrates the full workflow from investigation to task handoff.