Skip to main content

​
Welcome to IncidentFox

IncidentFox is an AI SRE / AI On-Call engineer that integrates with your observability stack, infrastructure, and collaboration tools to automatically investigate incidents, find root causes, and suggest fixes.

Quick Start

Get IncidentFox up and running in minutes

How It Works

Understand the multi-agent architecture

Configuration

Configure agents, tools, and prompts

Integrations

Connect to Slack, GitHub, PagerDuty, and more

​
Key Features

IncidentFox uses 6 specialized agents that work together:
  • Planner Agent - Orchestrates investigations and delegates tasks
  • K8s Agent - Kubernetes troubleshooting specialist
  • AWS Agent - AWS resource debugging
  • Metrics Agent - Anomaly detection and correlation
  • Coding Agent - Code analysis and CI/CD fixes
  • Investigation Agent - Comprehensive troubleshooting with 50+ tools
Pre-built integrations for your entire stack:
  • Kubernetes: Pod logs, events, deployments, resource usage
  • AWS: EC2, Lambda, RDS, ECS, CloudWatch
  • Observability: Grafana, Datadog, New Relic, Coralogix
  • Code: GitHub, Git, CI/CD pipelines
  • Data: Snowflake, Elasticsearch
Invoke IncidentFox from wherever your team works:
  • Slack - Mention the bot in any channel
  • GitHub - Comment on issues or PRs
  • PagerDuty - Automatic investigation on alerts
  • Incident.io - Integrated incident response
  • REST API - Programmatic access
Built for enterprise security and compliance:
  • SSO/OIDC authentication
  • Role-based access control (RBAC)
  • Approval workflows for changes
  • Full audit logging
  • Hierarchical team configuration

​
What Can IncidentFox Do?

​
Incident Investigation

When an incident occurs, IncidentFox automatically:
  1. Gathers Context - Pulls logs, metrics, and recent changes from your observability stack
  2. Analyzes Root Cause - Correlates data across services to identify the issue
  3. Provides Timeline - Reconstructs what happened and when
  4. Suggests Fixes - Recommends actionable remediation steps
@incidentfox investigate why the payments service is slow

​
CI/CD Auto-Fix

When your CI pipeline fails, IncidentFox can:
  1. Detect Failures - Monitors GitHub Actions, CodePipeline, and other CI systems
  2. Analyze Logs - Reads test output and build errors
  3. Identify Root Cause - Correlates failures with code changes in the PR
  4. Propose Fixes - Suggests code changes to resolve the issue

​
Proactive Monitoring

IncidentFox can monitor your systems and alert before issues escalate:
  • Anomaly Detection - Prophet-based forecasting identifies unusual patterns
  • Correlation Analysis - Links metrics across services to find relationships
  • Knowledge Base - Learns from your runbooks and past incidents

​
Getting Started

1

Connect Your Data Sources

Configure connections to your observability stack (Coralogix, Datadog, Grafana, etc.)
2

Set Up Integrations

Connect IncidentFox to Slack, GitHub, or PagerDuty for triggering investigations
3

Configure Your Team

Customize agent prompts and enable/disable tools for your specific needs
4

Start Investigating

Mention @incidentfox in Slack or trigger via your preferred integration

​
Support

Need help? Contact us at support@incidentfox.ai