Find failures fast with agent tracing
Quickly debug and understand non-deterministic LLM app behavior with tracing. See what your agent is doing step by step —then fix issues to improve latency and response quality.
Connect with an expert
LangSmith Observability
Know what your agents are really doing
LangSmith Observability gives you complete visibility into agent behavior with tracing, real-time monitoring, alerting, and high-level insights into usage.
LangSmith powers top engineering teams, from AI startups to global enterprises
.svg)
.svg)
.svg)
.svg)
.svg)
%201.svg){kind=logo}
.svg)
Monitor what matters to the business
Track business-critical metrics like costs, latency, and response quality with live dashboards. Get alerts when issues happen and drill into the root cause.
Get started now
Discover usage patterns and issues automatically
See clusters of similar conversations to understand what users actually want and quickly find all instances of similar problems to address systemic issues.
See it in action
Why top AI teams choose LangSmith
Visibility & control
See exactly what's happening at every step of your agent. Steer your agent to accomplish critical tasks the way you intended.
Fast iteration
Rapidly move through build, test, deploy, learn, repeat with workflows across the entire agent engineering lifecycle.
.svg)
Durable performance
Ship at scale with agent infrastructure designed for long-running workloads and human oversight.
Framework neutral
Keep your current stack. LangSmith works with your preferred open-source framework or custom code.
Ready to get visibility into your agents?
LangSmith works with any framework. If you’re already using LangChain or LangGraph, just set one environment variable to get started with tracing your AI application.