Build an agentic incident triage assistant with Amazon Quick and New Relic

2026-06-09 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & IT Infrastructure · Depth: Intermediate, long

Summary

An agentic incident triage assistant can be built using Amazon Quick and New Relic to streamline incident response workflows. This solution leverages Amazon Quick's native integrations with New Relic Model Context Protocol (MCP) Server and Asana to automate evidence collection, root cause analysis (RCA) brief generation, and task creation. From a single prompt, the Amazon Quick agent orchestrates five New Relic reasoning tools—including generate_alert_insights_report and analyze_entity_logs—to investigate incidents. It then compiles a comprehensive RCA brief with evidence links and creates a tracked Asana task for handoff. Internal testing by New Relic demonstrated that this agent reduced the evidence-gathering phase, leading to faster resolution, minimized knowledge loss, and standardized investigations across on-call rotations. Setting up requires an Amazon Quick Professional subscription, New Relic, and Asana accounts.

Key takeaway

For SREs or MLOps Engineers focused on reducing mean time to resolution (MTTR), implementing an Amazon Quick-based incident triage agent can significantly streamline your workflow. You can automate evidence gathering, root cause analysis brief generation, and task creation from a single prompt, ensuring consistent investigation standards across your team. This approach minimizes manual coordination between observability and tracking systems, freeing your engineers to focus on resolution rather than administrative overhead.

Key insights

An AI agent can automate incident triage by integrating observability and task management tools into a single conversational workflow.

Principles

• Agentic AI orchestrates disparate enterprise tools.
• Standardized incident investigation improves MTTR.
• Implement least privilege for agent integrations.

Method

Configure Amazon Quick with New Relic and Asana integrations. Create a custom chat agent, define its purpose and tool routing, then link the configured integrations to enable automated incident investigation and task creation.

In practice

• Use Amazon Quick for agentic workflows.
• Integrate New Relic for incident data analysis.
• Automate Asana task creation for handoff.

Topics

• Amazon Quick
• New Relic
• Incident Triage
• Agentic AI
• Site Reliability Engineering
• Root Cause Analysis

Best for: MLOps Engineer, AI Engineer, Director of AI/ML

Related on AIssential

• AWS Announces General Availability of DevOps Agent for Automated Incident Investigation — AWS DevOps Agent uses generative AI to autonomously investigate incidents and automate operational tasks across diverse environments.
• Using observability data to prevent incidents — Proactive reliability intelligence, enabled by rapid data access, prevents incidents by identifying risk trends before they manifest.
• STAR: A Stage-attributed Triage and Repair framework for RCA Agents in Microservices — Decomposing LLM-based RCA into stages enables precise error localization and targeted repair, improving reliability.
• Resolve AI says the AI coding boom is breaking production systems. It wants to fix that. — Multi-agent AI systems enhance production incident resolution by parallelizing investigations and cross-verifying conclusions.
• Building an Autonomous SRE Incident Response System Using AWS Strands Agents SDK — Multi-agent AI automates SRE incident response from alarm to remediation and reporting.
• Self-managed observability: Running agentic AI inside your boundary — Self-managed AI deployments necessitate robust internal observability for operational accountability and system reliability.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.