What is Edgedive?
Edgedive is an AI support engineer that integrates with your observability stack, cloud logs, and codebase to automatically investigate engineering alerts as they occur. Trigger an investigation by @tagging Edgedive in Slack or a ticket, assigning an issue to Edgedive, or letting it respond automatically to alerts from your connected sources. It cross-references logs, metrics, traces, code, and historical incidents to determine root cause, assess impact, and suggest fixes—before you start debugging.Gather Trigger Data
An alert fires or an issue is assigned to Edgedive. Trigger data—error messages, alert context, issue descriptions—is collected.
Gather Production Context
Edgedive queries logs, metrics, traces, and your codebase in parallel across all connected sources.
Root Cause Analysis
Signals are correlated with recent deployments, historical incidents, and code changes to identify the root cause.
Investigation Report
A structured report with root cause, impact analysis, incident timeline, and suggested remediation is delivered.
Edgedive completes its investigation before you open your laptop. Average investigation time: under 5 minutes.
Key Capabilities
- Cross-Signal Correlation — Queries logs, metrics, traces, and your codebase in parallel, then connects the dots across systems.
- On-Call Intelligence — Learns from past alerts and investigations to recognize patterns and improve accuracy over time.
- Unified Query Layer — Ask questions in natural language across all your production systems. No more switching between dashboards.
- Deep Investigation — Builds incident timelines, tests hypotheses, and aggregates evidence into structured reports.
Get Started
Quickstart
Investigate your first alert in minutes
Connections
Connect your tools, observability, and logs
How an Investigation Works
When an alert is triggered, Edgedive runs through a structured investigation pipeline:1. Signal Collection
- Fetches logs from your cloud provider (AWS CloudWatch, Azure Monitor, GCP)
- Pulls error details and stack traces from Sentry or Datadog
- Gathers metrics from Prometheus, Grafana, or Loki
- Reads recent commits and code changes from GitHub
2. Cross-Referencing
- Correlates error patterns with recent deployments
- Checks historical incidents for similar signatures
- Maps affected services and dependencies
- Identifies the most likely root cause
3. Investigation Report
- Root cause analysis — What went wrong and why
- Impact analysis — What’s affected and severity
- Incident timeline — Sequence of events leading to the issue
- Suggested remediation — How to fix it
You can also trigger investigations on-demand by @mentioning Edgedive in Slack or assigning an issue to Edgedive in your ticketing system.
Fix and Handoff
After investigation, Edgedive can take action:| Action | Description |
|---|---|
| One-click PR | Edgedive creates a branch, implements the fix, and opens a pull request |
| CLI takeover | Continue locally in your terminal with full session context |
Investigation Continuity
Edgedive maintains full context throughout an investigation:- Pause and resume investigations at any time
- Investigation context carries into fix/handoff workflows
- If something fails, retry with existing context preserved
- Historical investigations inform future root cause analysis
Security
SOC2 Type II
Fully compliant with SOC2 Type II standards
HIPAA Compliant
Meets HIPAA requirements for protected data
- All data encrypted in transit and at rest
- Logically isolated per customer
- No customer data used for model training