Features
Silent failure detection for hallucinations, loops, broken tools
Full trace capture: messages, tool calls, retries, errors
Trajectories viewer with natural language search (Deep Search)
Custom Signals for ground-truth monitoring
Slack-native interface: query, triage, signal creation
A/B Experiments against live traffic
Self-Healing Agents: auto-fix failures, convert to evals (2.0)
Triage: agent that investigates agent issues in Slack/web
Raindrop Workshop: OSS local debugger (MCP-native)
Agent Self Diagnostics: agents report own failures/capability gaps
Alerting with daily summaries and custom thresholds
Projects for isolating ingest, dashboards, AI features per org
Typescript, Python, Go, Rust, Java SDKs
REST API and browser JavaScript integration
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
