# Docs by LangChain: LangSmith

> Markdown index of the LangSmith documentation.

## LangSmith

- [Attribute-based access control](https://docs.langchain.com/langsmith/abac.md)
- [Access the current run (span) within a traced function](https://docs.langchain.com/langsmith/access-current-span.md)
- [Connect an authentication provider](https://docs.langchain.com/langsmith/add-auth-server.md)
- [Human-in-the-loop using server API](https://docs.langchain.com/langsmith/add-human-in-the-loop.md)
- [Add metadata and tags to traces](https://docs.langchain.com/langsmith/add-metadata-tags.md)
- [Account](https://docs.langchain.com/langsmith/admin.md): Set up your LangSmith account, including API keys, profile configuration, integrations, and pricing tiers.
- [Overview](https://docs.langchain.com/langsmith/administration-overview.md)
- [Set up Agent Auth](https://docs.langchain.com/langsmith/agent-auth.md): Enable secure access from agents to any system using OAuth 2.0 credentials with Agent Auth.
- [Agent Server changelog](https://docs.langchain.com/langsmith/agent-server-changelog-link.md)
- [Agent Server changelog](https://docs.langchain.com/langsmith/agent-server-changelog.md)
- [Distributed tracing with Agent Server](https://docs.langchain.com/langsmith/agent-server-distributed-tracing.md): Unify traces when calling your deployed Agent Server from another service using RemoteGraph or the SDK.
- [How to collect user feedback for Agent Server runs](https://docs.langchain.com/langsmith/agent-server-feedback.md)
- [Agent Server](https://docs.langchain.com/langsmith/agent-server-overview.md): Configure and operate the LangSmith Agent Server runtime, including capabilities, application structure, auth, and customization.
- [Configure Agent Server for scale](https://docs.langchain.com/langsmith/agent-server-scale.md): Tune the Agent Server for self-hosted deployments—write load, read load, and example Helm configurations for different load patterns.
- [Agent Server](https://docs.langchain.com/langsmith/agent-server.md)
- [Alerts in LangSmith](https://docs.langchain.com/langsmith/alerts.md)
- [Analyze an experiment](https://docs.langchain.com/langsmith/analyze-an-experiment.md)
- [Custom instrumentation](https://docs.langchain.com/langsmith/annotate-code.md): Instrument your code directly to control which functions are traced and how they appear in LangSmith.
- [Annotate traces and runs inline](https://docs.langchain.com/langsmith/annotate-traces-inline.md)
- [Manage feedback & annotation queues programmatically](https://docs.langchain.com/langsmith/annotation-queues-sdk.md)
- [Use annotation queues](https://docs.langchain.com/langsmith/annotation-queues.md)
- [Control plane API reference for LangSmith Deployment](https://docs.langchain.com/langsmith/api-ref-control-plane.md)
- [Application structure](https://docs.langchain.com/langsmith/application-structure.md)
- [Use assertions](https://docs.langchain.com/langsmith/assertions.md): Capture free-form acceptance criteria as dataset examples by writing assertions while reviewing runs in an annotation queue.
- [Assistants](https://docs.langchain.com/langsmith/assistants.md)
- [Log user feedback using the SDK](https://docs.langchain.com/langsmith/attach-user-feedback.md)
- [How to audit evaluator scores](https://docs.langchain.com/langsmith/audit-evaluator-scores.md)
- [Audit logs](https://docs.langchain.com/langsmith/audit-logs.md): Track and review administrative actions across your LangSmith organization for security, compliance, and operational visibility.
- [Authentication & access control](https://docs.langchain.com/langsmith/auth.md)
- [Authentication methods](https://docs.langchain.com/langsmith/authentication-methods.md)
- [Self-hosted LangSmith on AWS](https://docs.langchain.com/langsmith/aws-self-hosted.md)
- [Self-hosted LangSmith on Azure](https://docs.langchain.com/langsmith/azure-self-hosted.md)
- [How to kick off background runs](https://docs.langchain.com/langsmith/background-run.md)
- [Export trace data to BigQuery](https://docs.langchain.com/langsmith/big-query-bulk-export.md): Load LangSmith trace data into BigQuery using bulk export to GCS.
- [Manage billing in your account](https://docs.langchain.com/langsmith/billing.md)
- [Automatically run evaluators on experiments](https://docs.langchain.com/langsmith/bind-evaluator-to-dataset-link.md)
- [Automatically run evaluators on experiments](https://docs.langchain.com/langsmith/bind-evaluator-to-dataset.md)
- [BYOC architecture](https://docs.langchain.com/langsmith/byoc-architecture.md): How a LangSmith BYOC deployment is structured across the LangChain control plane and the data plane in your AWS account.
- [BYOC billing](https://docs.langchain.com/langsmith/byoc-billing.md): How LangSmith BYOC is billed across your AWS account and your LangSmith contract, which AWS services carry cost, and the account quotas to check before you deploy.
- [BYOC FAQ](https://docs.langchain.com/langsmith/byoc-faq.md): Answers to common questions about LangSmith BYOC, covering data residency, access, setup, the data plane model, and ongoing operations.
- [BYOC onboarding](https://docs.langchain.com/langsmith/byoc-onboarding.md): Set up a LangSmith BYOC data plane, from enabling BYOC on your organization to creating workspaces and connecting privately.
- [BYOC operations](https://docs.langchain.com/langsmith/byoc-operations.md): How LangChain upgrades, patches, and maintains a LangSmith BYOC data plane, and when maintenance requires a scheduled window.
- [BYOC usage](https://docs.langchain.com/langsmith/byoc-usage.md): Route tracing and API traffic to a LangSmith BYOC data plane, including tracing to multiple endpoints and the path prefixes for each service.
- [Why BYOC](https://docs.langchain.com/langsmith/byoc-why.md): Compare LangSmith BYOC with self-hosted LangSmith to decide which deployment model fits your organization.
- [Bring Your Own Cloud (BYOC)](https://docs.langchain.com/langsmith/byoc.md): Deploy LangSmith services and store data in your own cloud environment while LangChain operates, scales, and upgrades the infrastructure.
- [Use server-side caching](https://docs.langchain.com/langsmith/caching.md): Cache values server-side in your agent deployment using stale-while-revalidate and key-value cache APIs.
- [How to cancel a run](https://docs.langchain.com/langsmith/cancel-run.md): Cancel a single run or multiple runs via the API, and choose between interrupt and rollback actions.
- [LangSmith Cloud changelog](https://docs.langchain.com/langsmith/changelog.md): Weekly updates to LangSmith Cloud
- [LangSmith Chat](https://docs.langchain.com/langsmith/chat-evaluation.md): Use Chat to analyze evaluations and experiments.
- [LangSmith Chat](https://docs.langchain.com/langsmith/chat-observability.md): Use Chat to analyze traces and runs.
- [LangSmith Chat](https://docs.langchain.com/langsmith/chat-prompt-engineering.md): Use Chat to optimize prompts in the Playground.
- [LangSmith Chat](https://docs.langchain.com/langsmith/chat.md): Use Chat in LangSmith to analyze traces, threads, prompts, and evaluations.
- [Implement a CI/CD pipeline using LangSmith Deployment and Evaluation](https://docs.langchain.com/langsmith/cicd-pipeline-example.md)
- [LangGraph CLI](https://docs.langchain.com/langsmith/cli.md)
- [Cloud platform features](https://docs.langchain.com/langsmith/cloud-platform-features.md): Cloud-only platform features for LangSmith Deployment, including data regions, static IP addresses, payload limits, and deployment types.
- [Cloud (SaaS)](https://docs.langchain.com/langsmith/cloud.md)
- [How to define a code evaluator](https://docs.langchain.com/langsmith/code-evaluator-sdk.md)
- [How to define a code evaluator](https://docs.langchain.com/langsmith/code-evaluator-ui.md)
- [Coding agent metadata contract](https://docs.langchain.com/langsmith/coding-agent-metadata-contract.md): The metadata schema that standardizes what trace metadata coding agents must emit when sending runs to LangSmith.
- [How to compare experiment results](https://docs.langchain.com/langsmith/compare-experiment-results.md)
- [LangSmith Deployment components](https://docs.langchain.com/langsmith/components.md): Overview of Agent Server, LangGraph CLI, Studio, SDKs, RemoteGraph, control plane, and data plane components.
- [How to create a composite evaluator](https://docs.langchain.com/langsmith/composite-evaluators-sdk.md)
- [How to create a composite evaluator](https://docs.langchain.com/langsmith/composite-evaluators-ui.md)
- [Conditional tracing](https://docs.langchain.com/langsmith/conditional-tracing.md)
- [Use HTTP headers for runtime configuration](https://docs.langchain.com/langsmith/configurable-headers.md)
- [Include HTTP headers in server logs](https://docs.langchain.com/langsmith/configurable-logs.md)
- [Manage assistants](https://docs.langchain.com/langsmith/configuration-cloud.md)
- [Configure checkpointer backend](https://docs.langchain.com/langsmith/configure-checkpointer.md): Configure Agent Server to use PostgreSQL, MongoDB, or a custom implementation for checkpoint storage.
- [Configure IAM authentication for data stores](https://docs.langchain.com/langsmith/configure-iam-auth.md): Configure Agent Server to use cloud workload identities for PostgreSQL and Redis authentication.
- [Configure run input and output preview](https://docs.langchain.com/langsmith/configure-input-output-preview.md): Customize what appears in the Input and Output columns of the Runs table by configuring custom preview paths for specific trace types.
- [How to add TTLs to your application](https://docs.langchain.com/langsmith/configure-ttl.md)
- [Context engineering concepts](https://docs.langchain.com/langsmith/context-engineering-concepts.md): Core concepts for context engineering in LangSmith, including skills, agents, versioning, and sharing.
- [Configure Context Hub commit webhooks](https://docs.langchain.com/langsmith/context-hub-webhooks.md): Send Context Hub commit events to an external HTTPS endpoint and verify that LangSmith signed each request.
- [LangSmith control plane](https://docs.langchain.com/langsmith/control-plane.md)
- [Core capabilities overview](https://docs.langchain.com/langsmith/core-capabilities.md): Agent Server capabilities including streaming, human-in-the-loop, MCP, A2A, distributed tracing, webhooks, and double-texting.
- [Cost tracking](https://docs.langchain.com/langsmith/cost-tracking.md)
- [Create a prompt](https://docs.langchain.com/langsmith/create-a-prompt.md)
- [Create an account and API key](https://docs.langchain.com/langsmith/create-account-api-key.md)
- [How to improve your evaluator with few-shot examples](https://docs.langchain.com/langsmith/create-few-shot-evaluators.md)
- [Use cron jobs](https://docs.langchain.com/langsmith/cron-jobs.md)
- [Custom Apps](https://docs.langchain.com/langsmith/custom-apps.md): Build and deploy custom UIs that run inside LangSmith and talk to the LangSmith API.
- [Add custom authentication](https://docs.langchain.com/langsmith/custom-auth.md)
- [How to use a custom checkpointer](https://docs.langchain.com/langsmith/custom-checkpointer.md): Replace the built-in Postgres checkpointer with a custom BaseCheckpointSaver implementation in your agent deployment.
- [How to customize the Dockerfile](https://docs.langchain.com/langsmith/custom-docker.md)
- [Connect to a custom model](https://docs.langchain.com/langsmith/custom-endpoint.md)
- [How to add custom lifespan events](https://docs.langchain.com/langsmith/custom-lifespan.md)
- [How to add custom middleware](https://docs.langchain.com/langsmith/custom-middleware.md)
- [Connect to an OpenAI compliant model provider/proxy](https://docs.langchain.com/langsmith/custom-openai-compliant-model.md)
- [Custom output rendering](https://docs.langchain.com/langsmith/custom-output-rendering.md)
- [How to add custom routes](https://docs.langchain.com/langsmith/custom-routes.md)
- [Specify a custom run ID](https://docs.langchain.com/langsmith/custom-run-id.md): How to specify a custom run ID when tracing with LangSmith.
- [How to use a custom store](https://docs.langchain.com/langsmith/custom-store.md): Replace the built-in Postgres store with a custom BaseStore implementation in your agent deployment.
- [Monitor projects with dashboards](https://docs.langchain.com/langsmith/dashboards.md)
- [Manage bulk export destinations](https://docs.langchain.com/langsmith/data-export-destinations.md): Configure and manage S3-compatible export destinations for LangSmith bulk exports.
- [Import exported data](https://docs.langchain.com/langsmith/data-export-downstream.md): Import LangSmith bulk-exported Parquet data into BigQuery, Snowflake, Redshift, Clickhouse, or DuckDB.
- [Monitor and troubleshoot bulk exports](https://docs.langchain.com/langsmith/data-export-monitor.md): Monitor bulk export status, manage running exports, and troubleshoot failures.
- [Bulk export trace data](https://docs.langchain.com/langsmith/data-export.md): Export LangSmith trace data to an S3-compatible bucket in Parquet format.
- [LangSmith data plane](https://docs.langchain.com/langsmith/data-plane.md)
- [Data purging for compliance](https://docs.langchain.com/langsmith/data-purging-compliance.md)
- [Data storage and privacy](https://docs.langchain.com/langsmith/data-storage-and-privacy.md)
- [Dataset prebuilt JSON schema types](https://docs.langchain.com/langsmith/dataset-json-types.md)
- [Dataset transformations](https://docs.langchain.com/langsmith/dataset-transformations.md)
- [How to define a target function to evaluate](https://docs.langchain.com/langsmith/define-target-function.md)
- [Deploy with Cloudflare Workers](https://docs.langchain.com/langsmith/deploy-cloudflare-workers.md): Deploy a LangChain deep agent on Cloudflare Workers with Vite, React, Hono, and Durable Objects for SSE replay.
- [Deploy with Deno Deploy](https://docs.langchain.com/langsmith/deploy-deno.md): Deploy a LangChain deep agent on Deno Deploy with Hono route handlers and a Vite React SPA served from one entrypoint.
- [Deploy full-stack web apps](https://docs.langchain.com/langsmith/deploy-frameworks-and-platforms.md): Deploy LangChain agents as full-stack web apps on Next.js, SvelteKit, Nuxt, Cloudflare Workers, Deno Deploy, and Vite with streaming UI and thread history.
- [Deploy Google ADK agents](https://docs.langchain.com/langsmith/deploy-google-adk.md): Deploy Google Agent Development Kit (ADK) agents to LangSmith Agent Server using the deployments-wrap-sdk package.
- [Deploy with Next.js](https://docs.langchain.com/langsmith/deploy-nextjs.md): Deploy a LangChain deep agent in a Next.js App Router project with streaming chat, subagents, and thread history.
- [Deploy with Nuxt](https://docs.langchain.com/langsmith/deploy-nuxt.md): Deploy a LangChain deep agent in a Nuxt 4 app with Nitro server routes, Vue composables, and subagent-aware chat UI.
- [Deploy other frameworks](https://docs.langchain.com/langsmith/deploy-other-frameworks.md): Deploy agents built with Claude Agent SDK, Strands, CrewAI, AutoGen, and other frameworks to LangSmith Deployment.
- [Reference](https://docs.langchain.com/langsmith/deploy-reference-overview.md): Reference for the LangSmith Deployment SDKs, CLI, and APIs for deploying and interacting with agents.
- [Enable additional LangSmith features](https://docs.langchain.com/langsmith/deploy-self-hosted-full-platform.md): Enable LangSmith Deployment, Fleet, Insights, Chat, Sandboxes, and Engine on a self-hosted LangSmith instance.
- [Self-host standalone servers](https://docs.langchain.com/langsmith/deploy-standalone-server.md): Deploy standalone Agent Servers using Docker, Docker Compose, or Kubernetes without the LangSmith control plane.
- [Deploy with SvelteKit](https://docs.langchain.com/langsmith/deploy-sveltekit.md): Deploy a LangChain deep agent in a SvelteKit project on Cloudflare Workers with streaming chat and thread history.
- [Deploy to Cloud](https://docs.langchain.com/langsmith/deploy-to-cloud-overview.md): Deploy LangSmith agents to LangChain-managed Cloud infrastructure on AWS and GCP.
- [Deploy on Cloud](https://docs.langchain.com/langsmith/deploy-to-cloud.md): Create and manage LangSmith Cloud deployments including revisions, logs, metrics, and settings.
- [Deploy to self-hosted](https://docs.langchain.com/langsmith/deploy-to-self-hosted-overview.md): Run the LangSmith Deployment platform on your own infrastructure with full control over data, networking, and resources.
- [Deploy with LangSmith and Vite](https://docs.langchain.com/langsmith/deploy-vite-langsmith.md): Deploy a LangChain deep agent to LangSmith Deployment and stream from a Vite React chat UI on Vercel, Netlify, or Cloudflare Pages.
- [Deploy with control plane](https://docs.langchain.com/langsmith/deploy-with-control-plane.md): Build Docker images and deploy applications to a self-hosted LangSmith instance using the control plane UI.
- [Deploy Managed Deep Agents](https://docs.langchain.com/langsmith/deployment-quickstart-da.md)
- [Deploy your app to cloud](https://docs.langchain.com/langsmith/deployment-quickstart.md): Deploy your first application to LangSmith Cloud (AWS and GCP) using the LangGraph CLI.
- [LangSmith Deployment](https://docs.langchain.com/langsmith/deployment.md): Deploy and manage agents with durable execution, real-time streaming, and horizontal scaling.
- [Troubleshooting for self-hosted deployments](https://docs.langchain.com/langsmith/diagnostics-self-hosted.md): Diagnostic steps for troubleshooting self-hosted LangSmith Deployment issues before contacting support.
- [Implement distributed tracing](https://docs.langchain.com/langsmith/distributed-tracing.md)
- [Double texting](https://docs.langchain.com/langsmith/double-texting.md)
- [Add encryption at rest](https://docs.langchain.com/langsmith/encryption.md)
- [API and SDK deprecation policy](https://docs.langchain.com/langsmith/endpoint-deprecation.md): How LangSmith deprecates and removes API endpoints and SDK methods in cloud and self-hosted deployments.
- [Connect LangSmith Engine to GitHub](https://docs.langchain.com/langsmith/engine-github.md): Connect LangSmith Engine to GitHub in LangSmith Cloud, or create and configure your own GitHub App for a self-hosted deployment.
- [LangSmith Engine issue categories](https://docs.langchain.com/langsmith/engine-issue-categories.md): Reference for the issue categories LangSmith Engine assigns to detected issues, including descriptions and examples.
- [LangSmith Engine](https://docs.langchain.com/langsmith/engine-overview.md): LangSmith Engine is the agent for agent engineering, turning production traces into fixes, evaluators, and datasets across the development lifecycle.
- [LangSmith Engine security](https://docs.langchain.com/langsmith/engine-security.md): How LangSmith Engine handles your data, the GitHub and model subprocessor controls that govern its access, and its compliance posture.
- [LangSmith Engine on Self-hosted](https://docs.langchain.com/langsmith/engine-self-hosted.md): How LangSmith Engine runs in a self-hosted deployment, what it depends on outside your environment, and how it handles your data.
- [LangSmith Engine webhook events](https://docs.langchain.com/langsmith/engine-webhooks.md): Reference for the webhook events LangSmith Engine sends when it creates issues or links new traces to existing issues.
- [Find and fix your agent's issues with LangSmith Engine](https://docs.langchain.com/langsmith/engine.md): Automatically detect and resolve recurring issues in your tracing project using LangSmith Engine.
- [Enqueue concurrent](https://docs.langchain.com/langsmith/enqueue-concurrent.md)
- [LangSmith for Enterprise](https://docs.langchain.com/langsmith/enterprise.md): Hosting options, access control, data privacy, cost controls, and security compliance for Enterprise users.
- [Cloud Agent Server environment variables](https://docs.langchain.com/langsmith/env-var-cloud.md): Environment variables supported by the LangSmith Agent Server when deployed on Cloud.
- [Self-hosted Agent Server environment variables](https://docs.langchain.com/langsmith/env-var-self-hosted.md): Environment variables supported by the LangSmith Agent Server when deployed on self-hosted infrastructure.
- [Evaluate a chatbot](https://docs.langchain.com/langsmith/evaluate-chatbot-tutorial.md)
- [Evaluate a complex agent](https://docs.langchain.com/langsmith/evaluate-complex-agent.md)
- [How to add evaluators to an existing experiment (Python only)](https://docs.langchain.com/langsmith/evaluate-existing-experiment.md)
- [How to evaluate a graph](https://docs.langchain.com/langsmith/evaluate-graph.md)
- [How to evaluate agents](https://docs.langchain.com/langsmith/evaluate-llm-application.md)
- [How to evaluate an application's intermediate steps](https://docs.langchain.com/langsmith/evaluate-on-intermediate-steps.md)
- [How to run a pairwise evaluation](https://docs.langchain.com/langsmith/evaluate-pairwise.md)
- [Evaluate a RAG application](https://docs.langchain.com/langsmith/evaluate-rag-tutorial.md)
- [Run an evaluation with multimodal content](https://docs.langchain.com/langsmith/evaluate-with-attachments.md): Learn how to create dataset examples with file attachments and use them in prompts and evaluators when running LangSmith evaluations with multimodal content.
- [How to evaluate with OpenTelemetry](https://docs.langchain.com/langsmith/evaluate-with-opentelemetry.md)
- [How to retry failed runs in experiments (Python only)](https://docs.langchain.com/langsmith/evaluate-with-retry.md)
- [Application-specific evaluation approaches](https://docs.langchain.com/langsmith/evaluation-approaches.md)
- [How to run an evaluation asynchronously](https://docs.langchain.com/langsmith/evaluation-async.md)
- [Evaluation concepts](https://docs.langchain.com/langsmith/evaluation-concepts.md)
- [Evaluation quickstart](https://docs.langchain.com/langsmith/evaluation-quickstart.md)
- [Evaluation types](https://docs.langchain.com/langsmith/evaluation-types.md)
- [LangSmith Evaluation](https://docs.langchain.com/langsmith/evaluation.md): Evaluate and test agent quality at scale with datasets, evaluators, prompts, and Studio.
- [Track and limit evaluator spend](https://docs.langchain.com/langsmith/evaluator-spend.md): Cap weekly LLM spend on evaluators with an organization-wide default or per-evaluator overrides to keep evaluator costs predictable.
- [Manage evaluators](https://docs.langchain.com/langsmith/evaluators.md): View and manage evaluators at the workspace level in LangSmith.
- [Event streaming API](https://docs.langchain.com/langsmith/event-streaming.md): Stream LangSmith deployments with typed projections for messages, state, tool calls, subgraphs, and custom transformers.
- [Example data format](https://docs.langchain.com/langsmith/example-data-format.md)
- [Experiment configuration](https://docs.langchain.com/langsmith/experiment-configuration.md)
- [Export LangSmith telemetry to your observability backend](https://docs.langchain.com/langsmith/export-backend.md)
- [Query traces using the SDK](https://docs.langchain.com/langsmith/export-traces.md)
- [Frequently asked questions](https://docs.langchain.com/langsmith/faq.md)
- [Feedback data format](https://docs.langchain.com/langsmith/feedback-data-format.md)
- [How to fetch performance metrics for an experiment](https://docs.langchain.com/langsmith/fetch-perf-metrics-experiment.md)
- [How to filter experiments in the UI](https://docs.langchain.com/langsmith/filter-experiments-ui.md)
- [Filter traces](https://docs.langchain.com/langsmith/filter-traces-in-application.md)
- [Self-hosted LangSmith on GCP](https://docs.langchain.com/langsmith/gcp-self-hosted.md)
- [How to implement generative user interfaces with LangGraph](https://docs.langchain.com/langsmith/generative-ui-react.md)
- [Integrations](https://docs.langchain.com/langsmith/get-started-integrations.md)
- [Govern](https://docs.langchain.com/langsmith/govern-overview.md): Administer users, access control, organizational structure, and compliance policies for your LangSmith organization.
- [Governance](https://docs.langchain.com/langsmith/govern.md): Govern model access, spending, data handling, and compliance across your LangSmith organization.
- [Granular billable usage](https://docs.langchain.com/langsmith/granular-usage.md): Retrieve detailed trace and LangSmith Deployment usage data broken down by workspace, project, user, or API key.
- [Rebuild graph at runtime](https://docs.langchain.com/langsmith/graph-rebuild.md): Rebuild your graph with different configurations for each run using ServerRuntime.
- [How to handle model rate limits](https://docs.langchain.com/langsmith/handle-model-rate-limiting.md)
- [Harbor integrations](https://docs.langchain.com/langsmith/harbor-integrations.md): Run evaluations, Deep Agents, and sandboxes on LangSmith with Harbor.
- [Time travel using the server API](https://docs.langchain.com/langsmith/human-in-the-loop-time-travel.md)
- [Setup guide (legacy)](https://docs.langchain.com/langsmith/hybrid-legacy.md): Legacy hybrid deployment model with a LangChain-managed control plane and a self-managed data plane.
- [Hybrid](https://docs.langchain.com/langsmith/hybrid.md): A LangSmith Deployment setup where you self-host Agent Servers in your infrastructure and send traces to LangSmith Cloud or a self-hosted LangSmith instance.
- [Improve LLM-as-judge evaluators using human feedback](https://docs.langchain.com/langsmith/improve-judge-evaluator-feedback.md)
- [Discover errors and usage patterns with Insights](https://docs.langchain.com/langsmith/insights.md): Use LangSmith Insights to automatically analyze traces, detect usage patterns, identify common agent behaviors, and surface failure modes without manual trace review.
- [Integrations](https://docs.langchain.com/langsmith/integrations.md)
- [Interrupt concurrent](https://docs.langchain.com/langsmith/interrupt-concurrent.md)
- [Define a Managed Deep Agent](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-agent-definition.md): Configure the model and core capabilities of a Managed Deep Agent.
- [Connect a Managed Deep Agent to Slack](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-channels-slack.md): Start Managed Deep Agents runs from Slack messages and send responses to Slack conversations.
- [Connect Managed Deep Agents to channels](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-channels.md): Connect Managed Deep Agents to external messaging services that can start runs and receive responses.
- [Managed Deep Agents CLI reference](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-cli.md): Reference for mda commands, project files, and deploy behavior.
- [Deploy a Managed Deep Agent](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-deploy.md): Test and deploy a Managed Deep Agent with the mda CLI.
- [Evaluate Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-evals.md): Create and run Harbor evals for Managed Deep Agents.
- [Add identity to Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-identity.md): Authenticate callers to a Managed Deep Agents deployment with a LangSmith API key or Supabase.
- [Add instructions to Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-instructions.md): Define the system prompt for a Managed Deep Agent in instructions.md.
- [Develop locally with LangSmith Studio](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-local-development.md): Run and test a Managed Deep Agent locally with mda dev and LangSmith Studio.
- [Connect to MCP servers](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-mcp-connectors.md): Add tools from remote MCP servers to Managed Deep Agents.
- [Add memory to Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-memory.md): Opt in to deployment-shared durable memory for Managed Deep Agents.
- [Add custom middleware to Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-middleware.md): Add built-in or custom middleware to Managed Deep Agents projects.
- [Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-overview.md): Build your agent as a directory of files while LangSmith runs the harness and runtime.
- [Managed Deep Agents project structure](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-project-structure.md): Understand the files and directories in a Managed Deep Agents project.
- [Managed Deep Agents quickstart](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-quickstart.md): Create and deploy your first Managed Deep Agent with the mda CLI.
- [Add a sandbox to Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-sandboxes.md): Configure an isolated filesystem and shell for Managed Deep Agents.
- [Add schedules to Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-schedules.md): Declare managed cron schedules for Managed Deep Agents deployments.
- [Add skills to Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-skills.md): Add reusable task-specific instructions to a Managed Deep Agent.
- [Add custom tools to Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-tools.md): Define authored tools for Managed Deep Agents projects.
- [Add a custom search tool, memory, and a schedule](https://docs.langchain.com/langsmith/javascript/managed-deep-agents-tutorial.md): Replace provider search with a Tavily tool, then add durable memory and a daily schedule to the research assistant from the quickstart.
- [Managed Deep Agents](https://docs.langchain.com/langsmith/javascript/managed-deep-agents.md)
- [Manage user access in SSO organizations](https://docs.langchain.com/langsmith/jit-invite-sso.md)
- [Self-host LangSmith on Kubernetes](https://docs.langchain.com/langsmith/kubernetes.md)
- [How to evaluate a runnable](https://docs.langchain.com/langsmith/langchain-runnable.md)
- [LangGraph JS/TS SDK](https://docs.langchain.com/langsmith/langgraph-js-ts-sdk.md)
- [LangGraph Python SDK](https://docs.langchain.com/langsmith/langgraph-python-sdk.md)
- [LangSmith CLI](https://docs.langchain.com/langsmith/langsmith-cli.md): Query and manage LangSmith projects, traces, runs, datasets, evaluators, experiments, and threads from the terminal
- [Configure your collector for LangSmith telemetry](https://docs.langchain.com/langsmith/langsmith-collector.md)
- [LangSmith-managed ClickHouse](https://docs.langchain.com/langsmith/langsmith-managed-clickhouse.md)
- [LangSmith MCP Server](https://docs.langchain.com/langsmith/langsmith-mcp-server.md): Use the Model Context Protocol (MCP) server to let language models fetch conversation history, prompts, runs, datasets, experiments, and billing from LangSmith.
- [LangSmith Remote MCP](https://docs.langchain.com/langsmith/langsmith-remote-mcp.md): Connect MCP-compatible clients to LangSmith over OAuth, or authenticate programmatic clients with a LangSmith API key.
- [Trace with the Vercel AI SDK (Legacy)](https://docs.langchain.com/langsmith/legacy-trace-with-vercel-ai-sdk.md)
- [How to define an LLM-as-a-judge evaluator](https://docs.langchain.com/langsmith/llm-as-judge-sdk.md)
- [How to define an LLM-as-a-judge evaluator](https://docs.langchain.com/langsmith/llm-as-judge.md)
- [Set up the LLM auth proxy](https://docs.langchain.com/langsmith/llm-auth-proxy-self-hosted.md): Deploy an Envoy-based auth proxy that validates LangSmith-signed JWTs and routes LLM requests to your upstream provider or gateway.
- [Traces and access control](https://docs.langchain.com/langsmith/llm-gateway-access.md): Understand where gateway traces land and who can see and configure what.
- [Admin setup](https://docs.langchain.com/langsmith/llm-gateway-admin-setup.md): One-time organization setup to enable the LLM Gateway and grant user access.
- [API formats](https://docs.langchain.com/langsmith/llm-gateway-api-formats.md): Use OpenAI Chat Completions, Anthropic Messages, or OpenAI Responses requests to call models across providers through the LLM Gateway.
- [Set up coding agents](https://docs.langchain.com/langsmith/llm-gateway-coding-agents.md): Configure Claude Code, Codex, Gemini CLI, and Deep Agents Code to route LLM calls through the LLM Gateway.
- [Gateway Credits](https://docs.langchain.com/langsmith/llm-gateway-credits.md): Use Gateway Credits to access models without a provider key, just authenticate with LangSmith.
- [Custom model providers](https://docs.langchain.com/langsmith/llm-gateway-custom-providers.md): Route requests through the LLM Gateway to a custom OpenAI- or Anthropic-compatible endpoint, such as a self-hosted open-source model.
- [Data protection](https://docs.langchain.com/langsmith/llm-gateway-data-protection.md): Scan and redact PII and secrets from LLM requests before they reach providers.
- [Direct model access](https://docs.langchain.com/langsmith/llm-gateway-direct-model-access.md): Access provider APIs directly through provider-specific LLM Gateway paths without using the gateway standardization layer.
- [Model fallbacks](https://docs.langchain.com/langsmith/llm-gateway-fallbacks.md): Automatically retry a request against backup model configurations when the primary model rate-limits, errors, or returns another configured status code.
- [Per-customer policies](https://docs.langchain.com/langsmith/llm-gateway-header-policies.md): Split gateway spend caps and rate limits by a custom request header so each of your end customers gets its own limit under a single API key.
- [Monitor LLM Gateway spend](https://docs.langchain.com/langsmith/llm-gateway-monitoring.md): View and analyze LLM Gateway costs by user, API key, and model.
- [Quickstart](https://docs.langchain.com/langsmith/llm-gateway-quickstart.md): Make your first LLM Gateway request with cURL, Python, or TypeScript.
- [Rate limit policies](https://docs.langchain.com/langsmith/llm-gateway-rate-limit-policies.md): Limit the number of requests or tokens a user, workspace, or API key can send through the LLM Gateway in a rolling time window.
- [Spend policies](https://docs.langchain.com/langsmith/llm-gateway-spend-policies.md): Set cost limits on LLM usage across your organization and prevent runaway spend before it reaches providers.
- [LLM Gateway](https://docs.langchain.com/langsmith/llm-gateway.md): Access models across providers with one LangSmith API key while tracing calls and enforcing spend and data-protection policies.
- [Local development & testing](https://docs.langchain.com/langsmith/local-dev-testing.md): Compare langgraph dev and langgraph up for local development and production-like testing of Agent Server applications.
- [How to run an evaluation locally (Python only)](https://docs.langchain.com/langsmith/local.md)
- [Log LLM calls](https://docs.langchain.com/langsmith/log-llm-trace.md)
- [Log multimodal traces](https://docs.langchain.com/langsmith/log-multimodal-traces.md)
- [Log retriever traces](https://docs.langchain.com/langsmith/log-retriever-trace.md): Log retrieval steps in LangSmith traces for document-level visibility into your RAG pipeline.
- [Log traces to a specific project](https://docs.langchain.com/langsmith/log-traces-to-project.md): Route LangSmith traces to a named project instead of the default project using environment variables or the SDK.
- [Metadata parameters reference](https://docs.langchain.com/langsmith/ls-metadata-parameters.md)
- [Manage contexts with the SDK](https://docs.langchain.com/langsmith/manage-contexts-sdk.md): Use the LangSmith SDK to push, pull, list, and delete agent and skill repos in the Context Hub programmatically.
- [Create and manage datasets in the UI](https://docs.langchain.com/langsmith/manage-datasets-in-application.md)
- [How to create and manage datasets programmatically](https://docs.langchain.com/langsmith/manage-datasets-programmatically.md)
- [Manage datasets](https://docs.langchain.com/langsmith/manage-datasets.md)
- [Manage evaluators with the SDK](https://docs.langchain.com/langsmith/manage-evaluators-sdk.md): Create, retrieve, update, list, and delete LangSmith evaluators programmatically with the SDK.
- [Manage your organization using the API](https://docs.langchain.com/langsmith/manage-organization-by-api.md)
- [Manage prompts programmatically](https://docs.langchain.com/langsmith/manage-prompts-programmatically.md)
- [Manage prompts](https://docs.langchain.com/langsmith/manage-prompts.md): Manage prompt versions, environments, and access controls in LangSmith.
- [Manage a trace](https://docs.langchain.com/langsmith/manage-trace.md): Share traces publicly, and view server logs from the Details view in LangSmith.
- [Manage LangSmith with Terraform](https://docs.langchain.com/langsmith/manage-with-terraform.md): Use the official LangSmith Terraform provider to manage workspaces, access controls, resource tags, evaluators, run rules, and alert rules as code.
- [Configure prompt settings](https://docs.langchain.com/langsmith/managing-model-configurations.md)
- [Prevent logging of sensitive data in traces](https://docs.langchain.com/langsmith/mask-inputs-outputs.md)
- [Messages view integrations](https://docs.langchain.com/langsmith/messages-view-integrations.md): Frameworks and SDKs that render in the LangSmith Messages view and the metadata each one sets.
- [How to return categorical vs numerical metrics](https://docs.langchain.com/langsmith/metric-type.md)
- [Manage model configurations](https://docs.langchain.com/langsmith/model-configurations.md): Manage model configurations and control their availability across LangSmith features.
- [Monorepo support](https://docs.langchain.com/langsmith/monorepo-support.md)
- [How to simulate multi-turn interactions](https://docs.langchain.com/langsmith/multi-turn-simulation.md)
- [Include multimodal content in a prompt](https://docs.langchain.com/langsmith/multimodal-content.md)
- [Test multi-turn conversations](https://docs.langchain.com/langsmith/multiple-messages.md)
- [How to return multiple scores in one evaluator](https://docs.langchain.com/langsmith/multiple-scores.md)
- [Troubleshoot trace nesting](https://docs.langchain.com/langsmith/nest-traces.md)
- [Observability concepts](https://docs.langchain.com/langsmith/observability-concepts.md): How LangSmith structures observability data as runs, traces, threads, and trajectories, and how to send traces.
- [Trace an LLM application tutorial](https://docs.langchain.com/langsmith/observability-llm-tutorial.md): Add LangSmith observability to an LLM application across prototyping, beta testing, and production.
- [Tracing quickstart](https://docs.langchain.com/langsmith/observability-quickstart.md): Add LangSmith tracing to an LLM application in minutes.
- [Deploy an observability stack for your LangSmith deployment](https://docs.langchain.com/langsmith/observability-stack.md)
- [Observability in Studio](https://docs.langchain.com/langsmith/observability-studio.md)
- [LangSmith Observability](https://docs.langchain.com/langsmith/observability.md): Instrument your LLM application, investigate traces, and monitor performance in production with LangSmith.
- [Set up online code evaluators](https://docs.langchain.com/langsmith/online-evaluations-code.md)
- [Set up composite online evaluators](https://docs.langchain.com/langsmith/online-evaluations-composite.md)
- [Set up LLM-as-a-judge online evaluators](https://docs.langchain.com/langsmith/online-evaluations-llm-as-judge.md)
- [Set up multi-turn online evaluators](https://docs.langchain.com/langsmith/online-evaluations-multi-turn.md)