cross-link to langsmith (#4207)

npentrel · web-flow · commit eef2bcd3919f · 2026-05-29T17:16:28.000+02:00
diff --git a/src/oss/deepagents/backends.mdx b/src/oss/deepagents/backends.mdx
@@ -24,7 +24,6 @@ The `read_file` tool natively supports binary files (images, PDFs, audio, video)
 Sandboxes and the @[`LocalShellBackend`] also provide an `execute` tool.
 This page explains how to:
 
-
 - [choose a backend](#specify-a-backend),
 - [route different paths to different backends](#route-to-different-backends),
 - [implement your own virtual filesystem](#use-a-virtual-filesystem) (e.g., S3 or Postgres),
@@ -38,6 +37,12 @@ This page explains how to:
 - and [update existing backends to v2](#update-existing-backends-to-v2).
 :::
 
+<Tip>
+When you deploy on [LangSmith Deployment](/langsmith/deployment), a store is provisioned automatically. Use [LangSmith](/langsmith/home) tracing to debug file paths, permission denials, and cross-thread storage. Follow the [observability quickstart](/langsmith/observability-quickstart) to get set up.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine), which monitors your traces, detects issues, and proposes fixes.
+</Tip>
+
 ## Quickstart
 
 Here are a few prebuilt filesystem backends that you can quickly use with your deep agent:
diff --git a/src/oss/deepagents/code/overview.mdx b/src/oss/deepagents/code/overview.mdx
@@ -405,3 +405,7 @@ When configured, Deep Agents Code displays a status line with a link to the Lang
 ```sh
 ✓ LangSmith tracing: 'my-project'
 ```
+
+<Tip>
+We recommend you also set up [LangSmith Engine](/langsmith/engine), which monitors your traces, detects issues, and proposes fixes.
+</Tip>
diff --git a/src/oss/deepagents/customization.mdx b/src/oss/deepagents/customization.mdx
@@ -120,6 +120,12 @@ const agent = await createDeepAgent({
 For the full parameter list, see the [`createDeepAgent`](https://reference.langchain.com/javascript/deepagents/types/CreateDeepAgentParams) API reference. To compose a fully custom harness from scratch, see [Configure the harness](/oss/langchain/agents#configure-the-harness).
 :::
 
+<Tip>
+As you add tools, subagents, and backends, use [LangSmith](https://smith.langchain.com) to trace how each piece behaves together. Follow the [observability quickstart](/langsmith/observability-quickstart) to get set up, and see [Going to production](/oss/deepagents/going-to-production) for deployment on LangSmith.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine), which monitors your traces, detects issues, and proposes fixes.
+</Tip>
+
 ## Model
 
 Pass a `model` string in `provider:model` format, or an initialized model instance. See [supported models](/oss/deepagents/models#supported-models) for all providers and [suggested models](/oss/deepagents/models#suggested-models) for tested recommendations.
diff --git a/src/oss/deepagents/going-to-production.mdx b/src/oss/deepagents/going-to-production.mdx
@@ -12,7 +12,6 @@ import DeepagentsProductionInvokePy from '/snippets/code-samples/deepagents-prod
 
 This guide covers considerations for taking a deep agent from a local prototype to a production deployment. It walks through scoping memory, configuring execution environments, adding guardrails, and connecting a frontend.
 
-
 ## Overview
 
 Agents use information from memory and their execution environment to accomplish tasks.
@@ -36,6 +35,10 @@ This page covers:
 
 The recommended path for taking a Deep Agent to production is [Managed Deep Agents](/langsmith/deploy-managed-deep-agent), an API-first hosted runtime for creating, running, and operating deep agents in LangSmith. Managed Deep Agents is currently in private preview ([join the waitlist](https://www.langchain.com/langsmith-managed-deep-agents-waitlist)). For teams that need custom application code, custom routes, advanced authentication, or full Agent Server APIs, you can configure a [LangSmith Deployment](/langsmith/deployment) directly. Either path provisions the infrastructure your agent needs: [threads](/langsmith/use-threads), [runs](/langsmith/runs), a store, and a checkpointer, so you don't have to set these up yourself. A traditional LangSmith Deployment also gives you [authentication](/langsmith/auth), [webhooks](/langsmith/use-webhooks), [cron jobs](/langsmith/cron-jobs), and [observability](/langsmith/observability) out of the box, and can expose your agent via [MCP](/langsmith/server-mcp) or [A2A](/langsmith/server-a2a).
 
+<Tip>
+LangSmith Cloud deployments automatically send traces to a project named after your deployment. Open [LangSmith](https://smith.langchain.com) to debug runs and monitor usage. For hybrid or self-hosted setups, see [LangSmith tracing](/langsmith/data-plane#langsmith-tracing). We recommend you also set up [LangSmith Engine](/langsmith/engine), which monitors your traces, detects issues, and proposes fixes.
+</Tip>
+
 All code snippets on this page use the following `langgraph.json` unless otherwise specified:
 
 :::python
diff --git a/src/oss/deepagents/overview.mdx b/src/oss/deepagents/overview.mdx
@@ -32,10 +32,6 @@ Deep Agents is an ["agent harness"](/oss/concepts/products#agent-harnesses-like-
 
 See [Harness capabilities](/oss/deepagents/harness) for a full breakdown of each component.
 
-<Tip>
-  The [LangSmith Engine](/langsmith/engine) detects issues in your Deep Agents traces and proposes fixes. You can open a pull request with the proposed fix directly from the Engine tab.
-</Tip>
-
 :::python
 [`deepagents`](https://pypi.org/project/deepagents/) is a standalone library built on top of [LangChain](/oss/langchain/)'s core building blocks for agents. It uses the [LangGraph](/oss/langgraph/) runtime for durable execution, streaming, human-in-the-loop, and other features.
 :::
@@ -235,7 +231,7 @@ console.log(
 See the [Quickstart](/oss/deepagents/quickstart/) and [Customization guide](/oss/deepagents/customization/) to get started building your own agents and applications with Deep Agents.
 
 <Tip>
-Trace requests, debug agent behavior, and evaluate outputs with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up. When ready for production, [deploy to LangSmith Cloud](/langsmith/deploy-to-cloud) for managed hosting.
+Trace requests, debug agent behavior, and evaluate outputs with [LangSmith](https://smith.langchain.com). Follow the [observability quickstart](/langsmith/observability-quickstart) to get set up. When ready for production, see [Going to production](/oss/deepagents/going-to-production) for LangSmith deployment options.
 </Tip>
 
 ## Core capabilities
diff --git a/src/oss/deepagents/quickstart.mdx b/src/oss/deepagents/quickstart.mdx
@@ -155,6 +155,8 @@ Pass a `model` string in `provider:model` format, or an [initialized model insta
 
 <Tip>
 Trace your agent's planning steps, tool calls, and subagent delegation with [LangSmith](https://smith.langchain.com). Follow the [observability quickstart](/langsmith/observability-quickstart) to get set up.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine), which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## How does it work?
diff --git a/src/oss/deepagents/sandboxes.mdx b/src/oss/deepagents/sandboxes.mdx
@@ -68,6 +68,12 @@ These examples assume you have already created a sandbox/devbox using the provid
 <SandboxBasicPy />
 :::
 
+<Tip>
+[LangSmith](https://smith.langchain.com) traces show which shell commands ran inside a sandbox and how the agent used filesystem tools. Follow the [observability quickstart](/langsmith/observability-quickstart) to get set up. For managed sandbox hosting, see [LangSmith Sandboxes](/langsmith/sandboxes).
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine), which monitors your traces, detects issues, and proposes fixes.
+</Tip>
+
 ## Available providers
 
 :::python
diff --git a/src/oss/deepagents/skills.mdx b/src/oss/deepagents/skills.mdx
@@ -557,4 +557,6 @@ These are a few general guidelines for using tools and skills:
 
 <Tip>
 Trace how your agent discovers and executes skills with [LangSmith](https://smith.langchain.com). Follow the [observability quickstart](/langsmith/observability-quickstart) to get set up.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine), which monitors your traces, detects issues, and proposes fixes.
 </Tip>
diff --git a/src/oss/deepagents/subagents.mdx b/src/oss/deepagents/subagents.mdx
@@ -255,6 +255,10 @@ In this case the subagent with the name `"research-agent"`, will have `{'lc_agen
 
 ![LangSmith Example trace showing the metadata](/oss/images/deepagents/deepagents-langsmith.png)
 
+<Tip>
+Open the run in [LangSmith](https://smith.langchain.com) to compare the supervisor trace with each subagent run. Follow the [observability quickstart](/langsmith/observability-quickstart) to get set up. We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
+</Tip>
+
 ## Structured output
 
 Subagents support [structured output](/oss/langchain/structured-output), so the parent agent receives predictable, parseable JSON instead of free-form text.
@@ -1121,4 +1125,3 @@ const subagents = [
 ];
 ```
 :::
-:::
diff --git a/src/oss/langchain/agents.mdx b/src/oss/langchain/agents.mdx
@@ -170,7 +170,7 @@ To extend the agent's state schema with custom fields, use [`state_schema`](/oss
 ## Invocation
 
 <Tip>
-Trace each step of this loop, debug tool calls, and evaluate agent outputs with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.
+Trace each step of this loop, debug tool calls, and evaluate agent outputs with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up. We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 
diff --git a/src/oss/langchain/install.mdx b/src/oss/langchain/install.mdx
@@ -104,5 +104,5 @@ See the [Integrations tab](/oss/integrations/providers/overview) for a full list
 Now that you have LangChain installed, you can get started by following the [Quickstart guide](/oss/langchain/quickstart).
 
 <Tip>
-Set up [LangSmith](https://smith.langchain.com) tracing to debug your first LangChain app. Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get started.
+Set up [LangSmith](https://smith.langchain.com) tracing to debug your first LangChain app. Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get started. We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
diff --git a/src/oss/langchain/messages.mdx b/src/oss/langchain/messages.mdx
@@ -48,6 +48,12 @@ const response = await model.invoke(messages);  // Returns AIMessage
 ```
 :::
 
+<Tip>
+Multi-turn [agents](/oss/langchain/agents) accumulate long message histories. [LangSmith](/langsmith/home) records each turn, tool result, and model response so you can inspect the full conversation. Follow the [tracing quickstart](/langsmith/trace-with-langchain) to enable tracing.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
+</Tip>
+
 ### Text prompts
 
 Text prompts are strings - ideal for straightforward generation tasks where you don't need to retain conversation history.
diff --git a/src/oss/langchain/models.mdx b/src/oss/langchain/models.mdx
@@ -20,9 +20,13 @@ The quality and capabilities of the model you choose directly impact your agent'
 
 LangChain's standard model interfaces give you access to many different provider integrations, which makes it easy to experiment with and switch between models to find the best fit for your use case.
 
-<Info>
-    For provider-specific integration information and capabilities, see the provider's [chat model page](/oss/integrations/chat).
-</Info>
+For provider-specific integration information and capabilities, see the provider's [chat model page](/oss/integrations/chat).
+
+<Tip>
+[LangSmith](/langsmith/home) traces each model call so you can compare providers, inspect tool routing, and debug failures. Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
+</Tip>
 
 ## Basic usage
 
diff --git a/src/oss/langchain/multi-agent/index.mdx b/src/oss/langchain/multi-agent/index.mdx
@@ -97,6 +97,8 @@ Use this table to match your requirements to the right pattern:
 
 <Tip>
 Trace the full coordination flow across agents with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## Performance comparison
diff --git a/src/oss/langchain/overview.mdx b/src/oss/langchain/overview.mdx
@@ -15,11 +15,7 @@ Use [LangChain](/oss/langchain/agents) (`create_agent`) for a highly customizabl
 
 Use [LangGraph](/oss/langgraph/overview), our low-level orchestration framework, for advanced needs combining deterministic and agentic workflows.
 
-Use [LangSmith](/langsmith/home) to trace, debug, and evaluate agents built with any of these frameworks. Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.
-</Tip>
-
-<Tip>
-  The [LangSmith Engine](/langsmith/engine) detects issues in your LangChain agent traces and proposes fixes. You can open a pull request with the proposed fix directly from the Engine tab.
+Use [LangSmith](/langsmith/home) to trace, debug, and evaluate agents built with any of these frameworks. Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up. We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## <Icon icon="wand" /> Create an agent
diff --git a/src/oss/langchain/quickstart.mdx b/src/oss/langchain/quickstart.mdx
@@ -587,7 +587,9 @@ When you run the code and prompt the agent to tell you about the weather in San
 The agent understands that you are asking about the weather for the city San Francisco and therefore calls the weather tool with the provided city name.
 
 <Tip>
-You can use [any supported model](/oss/integrations/providers/overview) by changing the model name and setting up the appropriate API key. Trace what's happening inside your agent with [LangSmith](https://smith.langchain.com)—follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.
+You can use [any supported model](/oss/integrations/providers/overview) by changing the model name and setting up the appropriate API key. Trace what is happening inside your agent with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## Build a real-world agent
@@ -1373,7 +1375,9 @@ export LANGSMITH_API_KEY="..."
 Once set, run your script again and then inspect what happened during your agent calls on [LangSmith](https://smith.langchain.com) .
 
 <Tip>
-    To learn more about tracing your agent with LangSmith, see the [LangSmith documentation](/langsmith/trace-with-langchain).
+To learn more about tracing your agent with LangSmith, see the [LangSmith documentation](/langsmith/trace-with-langchain).
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## Next steps
diff --git a/src/oss/langchain/rag.mdx b/src/oss/langchain/rag.mdx
@@ -271,6 +271,10 @@ os.environ["LANGSMITH_API_KEY"] = getpass.getpass()
 ```
 :::
 
+<Tip>
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
+</Tip>
+
 ### Components
 
 We will need to select three components from LangChain's suite of integrations.
diff --git a/src/oss/langchain/tools.mdx b/src/oss/langchain/tools.mdx
@@ -19,7 +19,9 @@ Tools extend what [agents](/oss/langchain/agents) can do—letting them fetch re
 Under the hood, tools are callable functions with well-defined inputs and outputs that get passed to a [chat model](/oss/langchain/models). The model decides when to invoke a tool based on the conversation context, and what input arguments to provide.
 
 <Tip>
-For details on how models handle tool calls, see [Tool calling](/oss/langchain/models#tool-calling). Trace tool calls and debug errors with [LangSmith](https://smith.langchain.com)—follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.
+For details on how models handle tool calls, see [Tool calling](/oss/langchain/models#tool-calling). Trace tool calls and debug errors with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## Create tools
diff --git a/src/oss/langgraph/overview.mdx b/src/oss/langgraph/overview.mdx
@@ -100,7 +100,7 @@ await graph.invoke({ messages: [{ role: "user", content: "hi!" }] });
 :::
 
 <Tip>
-Use [LangSmith](/langsmith/home) to trace requests, debug agent behavior, and evaluate outputs. Set `LANGSMITH_TRACING=true` and your API key to get started.
+Use [LangSmith](/langsmith/home) to trace requests, debug agent behavior, and evaluate outputs. Set `LANGSMITH_TRACING=true` and your API key to get started. Follow the [tracing quickstart](/langsmith/trace-with-langchain) to get set up.  We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## Core benefits
diff --git a/src/oss/langgraph/persistence.mdx b/src/oss/langgraph/persistence.mdx
@@ -19,7 +19,7 @@ When using the [Agent Server](/langsmith/agent-server), you don't need to implem
 </Info>
 
 <Tip>
-Trace checkpointed state and debug how your agent resumes across sessions with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langgraph) to get set up.
+Trace checkpointed state and debug how your agent resumes across sessions with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langgraph) to get set up. We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## Why use persistence
diff --git a/src/oss/langgraph/quickstart.mdx b/src/oss/langgraph/quickstart.mdx
@@ -400,6 +400,8 @@ for (const message of result.messages) {
 
 <Tip>
 Trace and debug your agent with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langgraph) to get set up. When ready for production, see [Deploy](/langsmith/deployment) for hosting options.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 Congratulations! You've built your first agent using the LangGraph Graph API.
@@ -982,6 +984,8 @@ for (const message of result) {
 
 <Tip>
 Trace and debug your agent with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langgraph) to get set up. When ready for production, see [Deploy](/langsmith/deployment) for hosting options.
+
+We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 Congratulations! You've built your first agent using the LangGraph Functional API.
diff --git a/src/oss/langgraph/workflows-agents.mdx b/src/oss/langgraph/workflows-agents.mdx
@@ -3,7 +3,6 @@ title: Workflows and agents
 sidebarTitle: Workflows + agents
 ---
 
-
 This guide reviews common workflow and agent patterns.
 
 - Workflows have predetermined code paths and are designed to operate in a certain order.
@@ -14,7 +13,7 @@ This guide reviews common workflow and agent patterns.
 LangGraph offers several benefits when building agents and workflows, including [persistence](/oss/langgraph/persistence), [streaming](/oss/langgraph/streaming), and support for debugging as well as [deployment](/oss/langgraph/deploy).
 
 <Tip>
-Trace and compare these workflow patterns with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langgraph) to see how data flows through each step.
+Trace and compare these workflow patterns with [LangSmith](https://smith.langchain.com). Follow the [tracing quickstart](/langsmith/trace-with-langgraph) to see how data flows through each step. We recommend you also set up [LangSmith Engine](/langsmith/engine) which monitors your traces, detects issues, and proposes fixes.
 </Tip>
 
 ## Setup
