Introducing Detective

Prevent outages
in production.

Every regression is caught. Before your customers notice.

View DemoSign up
#alerts
RocketGraph
RocketGraph DetectiveAPPToday at 3:42 AM
Health: CRITICAL|Deploy #4821|542,847 logs analyzed|Wake on-call: YES

Summary

Critical issues detected: database deletion and DataNode exceptions. Immediate investigation required.

Anomaly insights

[amazon-store-local] cluster 7NEW

Critical data loss due to entire database deletion.

> 081109 203615 INFO deleted entire database

[amazon-store-local] cluster 8

Potential data transfer issues due to exceptions in DataNode.

> WARN DataNode$DataXceiver: Got exception while serving blk_168...

[amazon-store-local] cluster 13

Blocks marked as invalid could indicate data corruption.

> INFO FSNamesystem: BLOCK* NameSystem.delete: blk_197944... added to invalidSet

Recommended actions

  1. Investigate and restore the deleted database immediately.
  2. Check DataNode logs for root causes of exceptions.
  3. Review block invalidation logs to ensure data integrity.
👀3
🚨2
Log Clustering

Terabytes of logs. Hundreds of patterns.

Detective clusters your logs into digestible pattern snapshots. Feed them to Claude Code, your custom agents, or any AI tool to debug faster. No more drowning in raw logs.

  • Clusters by semantic similarity, not keywords
  • Export snapshots for AI agents like Claude Code
  • Spot new patterns after each deployment
  • Find what broke without reading millions of lines

Ingest from

Datadog
New Relic
Sentry
Loki
OpenTelemetry

Cluster

DB
HTTP
Auth
Cache
PatternsAnomaly

Deploy with confidence

Every deploy triggers an ML analysis. Regressions are caught in minutes, not days.

Ingest
DatadogDatadog
New RelicNew Relic
SentrySentry
LokiLoki
K8s Deploys
Analyze
ML Engine
Log Clustering
Isolation Forest
Anomaly Scoring
Integrate
Webhooks

Claude agents

Custom bots

Slack/Discord

Alert
Alert Gate

LLM filter

Noise reduction

Smart routing

Pull logs from your existing observability stack and deployment events from Kubernetes

Vectorize, cluster, and score anomalies using log clustering and Isolation Forest

Send to your agents via webhooks - Claude, custom bots, or any integration

A lightweight LLM decides if an alert is worth sending to reduce noise

Simple, transparent pricing

Start free. No credit card. No YAML.

Free Trial

Try it out

Full access for 7 days, no card required.

$0 / 7 days
  • All Pro features included
  • Up to 50M logs
  • Slack bot + anomaly detection
  • Auto-provisioned stack
  • No credit card needed
Start free trial
Most Popular

Pro

For growing teams

Everything you need to stop looking at logs.

$50 / month
  • Up to 50M logs/month
  • Slack conversational AI
  • Self-healing PR generation
  • ML anomaly detection
  • Full observability stack
  • Webhook integrations
  • 30-day retention
  • Priority support
Start free trial

Enterprise

Large-scale deployments

Custom volume, SLAs, and dedicated support.

Custom
  • Unlimited logs/month
  • Everything in Pro
  • Custom data retention
  • SSO & SAML
  • Dedicated Slack support
  • SLA guarantee
  • On-prem option
Talk to sales

Stop searching. Start finding.

Let Detective surface the anomalies that matter. No more manual log trawling during incidents.

View DemoSign up