For the complete documentation index, see llms.txt. This page is also available as Markdown.
🤖Overview
AI-powered incident investigation that connects to your entire stack and resolves issues from Slack.
Pagerly's SRE AI Agent is an AI-powered assistant that investigates incidents, queries your observability stack, and identifies root causes — all from a single Slack message.
Instead of manually jumping between Grafana, Datadog, Kubernetes, and your CI/CD pipeline during an incident, the agent does it for you in seconds.
How It Works
You report an issue → @Pagerly assist seems people are having issues with billing on dashboard
The agent investigates → It creates an investigation plan, queries your connected data sources (logs, metrics, traces, deployments), and correlates signals across tools
You get a root cause report → A structured incident report with timeline, root cause, and evidence — right in the Slack thread
Key Features
Natural language queries — Ask in plain English, no need to write PromQL or LogQL
Multi-tool correlation — Automatically queries logs, metrics, traces, deployments, and code changes in parallel
Structured reports — Produces incident reports with timelines, root cause, and evidence links
Team-scoped — Each team maps their own data sources, so the agent only queries what's relevant
40+ integrations — Connects to your entire observability, infra, CI/CD, and code stack
Getting Started
1. Connect Data Sources
Connect your observability tools, databases, and infrastructure to give the agent access to your stack.
2. Map to Teams
Assign integrations to specific on-call teams so the agent queries the right data for each team.
3. Use the Agent
Mention @Pagerly assist in any Slack channel to start an investigation.
