Features
Automated monitoring of production logs, metrics, and data
Anomaly detection for silent data correctness issues (table monitoring, SDK metrics)
Alert de-noising and false positive filtering via sub-agents
Root-cause analysis with documented investigation steps and citations
AI-suggested code fixes and PR creation
Persistent organization memory that learns from past issues and human feedback
PII masking for sensitive data (email, API keys, credit cards, etc.)
MCP server for connecting AI agents (remote or local)
CLI with machine-readable --json mode for scripting and agent integration
Bulk close stale issues in one operation
Slack & Teams notifications and ad-hoc investigations
On-premises and BYOC deployment options
Role-based access control (RBAC), SSO, SCIM provisioning, audit logs
Custom PII masking and BYOK support
Trace agent executions step by step
Monitor real-time dashboards with cost tracking
Online LLM-as-judge evals for quality scoring
Automated insights with unsupervised topic clustering
SmithDB purpose-built for agent traces
Sub-second query performance across millions of traces
Full-text search with inverted index
JSON key-path filtering and trajectory queries
Self-host SmithDB inside your VPC
LangSmith Engine for autonomous issue detection and fixes
Deploy and scale agents with LangSmith Deployment
Sandboxes for safe agent-generated code execution
Fleet agents for no-code agent creation
Supports Python, TypeScript, Go, Java SDKs
