LangSmith
LangSmith is a framework-agnostic platform for building, debugging, and deploying AI agents and LLM applications. Trace requests, evaluate outputs, test prompts, and manage deployments all in one place at smith.langchain.com.
When to use
Use LangSmith when you need to:
- Trace and debug LLM calls, agent steps, retrieval, and tool use
- Evaluate LLM outputs with automated or human-in-the-loop scoring
- Engineer prompts with a visual playground and version control
- Deploy agents to production with the LangGraph-based agent server
- Monitor production systems with dashboards, alerts, and cost tracking
When NOT to use
- To build agent logic or LLM pipelines, use LangChain, LangGraph, or Deep Agents instead
- LangSmith is the platform layer that complements these frameworks
Quick setup
Set two environment variables to enable tracing from any supported framework:
export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY="your-api-key" # from smith.langchain.com/settings
Install the SDK
# Python
pip install langsmith
# JavaScript/TypeScript
npm install langsmith
Verify tracing
from langsmith import traceable
@traceable
def my_function(query: str) -> str:
# Your LLM logic here—all calls inside are traced automatically
return "result"
Core capabilities
| Capability |
Description |
| Observability |
Trace every step of your LLM app with automatic or manual instrumentation |
| Evaluation |
Run evaluations with code, LLM-as-judge, or composite evaluators |
| Prompt engineering |
Create, version, and test prompts in a visual playground |
| Agent deployment |
Deploy LangGraph agents with streaming, human-in-the-loop, and durable execution |
| Monitoring |
Dashboards, alerts, and cost tracking for production workloads |
Key documentation
API reference
For SDK class and method details, use the LangChain API Reference site:
- Browse:
https://reference.langchain.com/python/langsmith
- MCP server:
https://reference.langchain.com/mcp
Related skills
- langchain—Build agents with prebuilt architecture and model integrations
- langgraph—Orchestrate stateful, durable agent workflows
- deep-agents—Batteries-included agent harness with planning and subagents
1---2name: langsmith3description: Trace, evaluate, and deploy AI agents and LLM applications with LangSmith. Use when adding observability, running evaluations, engineering prompts, or deploying agents to production.4license: MIT5compatibility: Framework-agnostic. Works with LangChain, LangGraph, Deep Agents, OpenAI Agents SDK, CrewAI, Pydantic AI, and more.6metadata:7 source: https://skillmd.com/skills/langchain-ai/langsmith8 author: langchain-ai9 version: "1.0"10---1112# LangSmith1314LangSmith is a framework-agnostic platform for building, debugging, and deploying AI agents and LLM applications. Trace requests, evaluate outputs, test prompts, and manage deployments all in one place at [smith.langchain.com](https://smith.langchain.com).1516## When to use1718Use LangSmith when you need to:19- **Trace and debug** LLM calls, agent steps, retrieval, and tool use20- **Evaluate** LLM outputs with automated or human-in-the-loop scoring21- **Engineer prompts** with a visual playground and version control22- **Deploy agents** to production with the LangGraph-based agent server23- **Monitor** production systems with dashboards, alerts, and cost tracking2425## When NOT to use2627- To build agent logic or LLM pipelines, use [LangChain](https://docs.langchain.com/oss/langchain/overview), [LangGraph](https://docs.langchain.com/oss/langgraph/overview), or [Deep Agents](https://docs.langchain.com/oss/deepagents/overview) instead28- LangSmith is the **platform layer** that complements these frameworks2930## Quick setup3132Set two environment variables to enable tracing from any supported framework:3334```bash35export LANGSMITH_TRACING=true36export LANGSMITH_API_KEY="your-api-key" # from smith.langchain.com/settings37```3839### Install the SDK4041```bash42# Python43pip install langsmith4445# JavaScript/TypeScript46npm install langsmith47```4849### Verify tracing5051```python52from langsmith import traceable5354@traceable55def my_function(query: str) -> str:56 # Your LLM logic here—all calls inside are traced automatically57 return "result"58```5960## Core capabilities6162| Capability | Description |63|-----------|-------------|64| Observability | Trace every step of your LLM app with automatic or manual instrumentation |65| Evaluation | Run evaluations with code, LLM-as-judge, or composite evaluators |66| Prompt engineering | Create, version, and test prompts in a visual playground |67| Agent deployment | Deploy LangGraph agents with streaming, human-in-the-loop, and durable execution |68| Monitoring | Dashboards, alerts, and cost tracking for production workloads |6970## Key documentation7172- [Overview](https://docs.langchain.com/langsmith/observability)—Get started with LangSmith73- [Observability quickstart](https://docs.langchain.com/langsmith/observability-quickstart)—Add tracing in minutes74- [Evaluation quickstart](https://docs.langchain.com/langsmith/evaluation-quickstart)—Run your first evaluation75- [Prompt engineering quickstart](https://docs.langchain.com/langsmith/prompt-engineering-quickstart)—Iterate on prompts76- [Deployment quickstart](https://docs.langchain.com/langsmith/deployment-quickstart)—Deploy an agent77- [Integrations](https://docs.langchain.com/langsmith/integrations)—Connect your framework or provider78- [Create account & API key](https://docs.langchain.com/langsmith/create-account-api-key)—Account setup7980## API reference8182For SDK class and method details, use the [LangChain API Reference](https://reference.langchain.com) site:83- Browse: `https://reference.langchain.com/python/langsmith`84- MCP server: `https://reference.langchain.com/mcp`8586## Related skills8788- **langchain**—Build agents with prebuilt architecture and model integrations89- **langgraph**—Orchestrate stateful, durable agent workflows90- **deep-agents**—Batteries-included agent harness with planning and subagents