LangSmith docs

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, with your agent stack.

Get started

1. Create an account

   Sign up at smith.langchain.com (no credit card required). You can log in with Google, GitHub, or email.

2. Create an API key

   Go to your Settings page → API Keys → Create API Key. Copy the key and save it securely.

3. Choose your integration

   LangSmith works with many frameworks and providers. Browse available integrations to connect your stack.

Once your account and API key are ready, choose a quickstart to begin building with LangSmith:

Observability

Gain visibility into every step your application takes to debug faster and improve reliability.

Start tracing

Evaluation

Measure and track quality over time to ensure your AI applications are consistent and trustworthy.

Evaluate your app

Deployment

Deploy your agents as Agent Servers, ready to scale in production.

Deploy your agents

More ways to build

Fleet

Design and deploy AI agents visually without writing code.

Build an agent

Prompt engineering

Iterate on prompts with built-in versioning and collaboration to ship improvements faster.

Test your prompts

LangSmith CLI

Query and manage traces, datasets, experiments, and more from the terminal.

Use the CLI

Studio

Use a visual interface to design, test, and refine applications end-to-end.

Develop with Studio

Infrastructure

Platform setup

Use LangSmith in managed cloud, in a self-hosted environment, or hybrid to match your infrastructure and compliance needs.

Choose how to set up LangSmith

Security & compliance

LangSmith meets the highest standards of data security and privacy with HIPAA, SOC 2 Type 2, and GDPR compliance. Meet with our team to learn more or visit our Trust Center.

Visit Trust Center

Workflow

LangSmith combines observability, evaluation, deployment, and platform setup in one integrated workflow—from local development to production.

---

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Edit this page on GitHub or file an issue.