Find the needle in the log haystack
Detective uses ML to surface the anomalies that matter from millions of noisy telemetry events.
#4821|542,847 logs analyzed|Wake on-call: YESSummary
Critical issues detected: database deletion and DataNode exceptions. Immediate investigation required.
Anomaly insights
Critical data loss due to entire database deletion.
> 081109 203615 INFO deleted entire database
Potential data transfer issues due to exceptions in DataNode.
> WARN DataNode$DataXceiver: Got exception while serving blk_168...
Blocks marked as invalid could indicate data corruption.
> INFO FSNamesystem: BLOCK* NameSystem.delete: blk_197944... added to invalidSet
Recommended actions
- Investigate and restore the deleted database immediately.
- Check DataNode logs for root causes of exceptions.
- Review block invalidation logs to ensure data integrity.
Detective compares log patterns before and after each deployment to surface unusual changes in real time.
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
Cluster
Lower depth = easier to isolate = more anomalous
Detect contamination in your log data
Isolation Forest is an unsupervised ML algorithm that isolates anomalies by randomly partitioning data. Anomalies are easier to isolate, requiring fewer splits. Detective uses this to find contamination - logs that do not fit the normal patterns of your system.
- No training data required - fully unsupervised
- Isolates anomalies with fewer random splits
- Scores each log by isolation depth
- Works on high-dimensional log vectors
The Detective Pipeline
From ingestion to alerting - how your logs flow through Detective
Datadog
LokiClaude agents
Custom bots
Slack/Discord
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
Pay based on your log ingestion volume. Start free and scale as you grow.
Starter
For small projects and testing
- Up to 1M logs/month
- 7-day retention
- Community support
Pro
For growing teams
- Up to 50M logs/month
- Everything in Starter
- Log clustering
- Isolation Forest detection
- Webhook integrations
- LLM alert filtering
- 30-day retention
- Priority support
Enterprise
For large-scale deployments
- Unlimited logs/month
- Everything in Pro
- Custom retention
- SSO & SAML
- Dedicated support
- SLA guarantee