langwatch · rogeriochaves · Mar 17, 2026 · Mar 11, 2026 · Mar 11, 2026 · Mar 15, 2026
diff --git a/agent-simulations/getting-started.mdx b/agent-simulations/getting-started.mdx
@@ -2,6 +2,10 @@
 title: Getting Started
 ---
 
+<Tip>
+  **Quick setup?** [Copy the scenarios prompt](/skills/code-prompts#add-scenario-tests) into your coding agent to add simulation tests automatically.
+</Tip>
+
 This guide will walk you through the basic setup required to run your first simulation and see the results in LangWatch.
 
 For more in-depth information and advanced use cases, please refer to the official [`scenario` library documentation](https://github.com/langwatch/scenario).

diff --git a/agent-simulations/introduction.mdx b/agent-simulations/introduction.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Introduction
 keywords: langwatch, agent simulations, agent testing, agent development, agent development, agent testing
 ---
 
+<Tip>
+  **Quick setup?** [Copy the scenarios prompt](/skills/code-prompts#add-scenario-tests) into your coding agent to add simulation tests automatically.
+</Tip>
+
 # What are Agent Simulations?
 
 Agent simulations are a powerful approach to testing AI agents that goes beyond traditional evaluation methods. Unlike static input-output testing, simulations test your agent's behavior in realistic, multi-turn conversations that mimic how real users would interact with your system.

diff --git a/better-agents/overview.mdx b/better-agents/overview.mdx
@@ -10,7 +10,7 @@ Better Agents is a CLI tool and a set of standards for building **reliable, test
 Use your preferred stack—Agno, Mastra, Vercel AI, Google ADK, or anything else. Better Agents doesn't replace your stack, it stabilizes it.
 
 <Note>
-Already have a project? Add evaluations, observability, and scenarios to your existing agent project. See the [Integration Guide](/integration/overview) to get started.
+  **Already have an agent?** You don't need Better Agents -- go to [LangWatch Skills](/skills/directory) to add tracing, evaluations, scenarios, and prompt versioning to your existing project.
 </Note>
 
 ## Quick Start

diff --git a/datasets/overview.mdx b/datasets/overview.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Overview
 description: Create and manage datasets in LangWatch to build evaluation sets for LLMs and structured AI agent testing.
 ---
 
+<Tip>
+  **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+</Tip>
+
 ## Create datasets
 
 LangWatch allows you to create and manage datasets, with a built-in excel-like interface for collaborating with your team.

diff --git a/docs.json b/docs.json
@@ -17,7 +17,7 @@
   },
   "favicon": "/favicon.svg",
   "banner": {
-    "content": "**[LangWatch MCP is live](https://langwatch.ai/docs/integration/mcp):** Your AI coding assistant can now build, version, and ship evals — no platform context-switching required.",
+    "content": "**[LangWatch MCP is live](https://langwatch.ai/docs/integration/mcp):** Your AI coding assistant can now build, version, and ship evals \u2014 no platform context-switching required.",
     "dismissible": true
   },
   "contextual": {
@@ -58,8 +58,17 @@
             "group": "Get Started",
             "pages": [
               "introduction",
-              "better-agents/overview",
-              "integration/mcp"
+              {
+                "group": "LangWatch Skills",
+                "pages": [
+                  "skills/directory",
+                  "skills/code-prompts",
+                  "skills/platform-prompts",
+                  "skills/recipes"
+                ]
+              },
+              "integration/mcp",
+              "better-agents/overview"
             ]
           },
           {
@@ -717,6 +726,26 @@
     {
       "source": "/hybrid-setup/sso-setup-langwatch",
       "destination": "/self-hosting/sso-setup-langwatch"
+    },
+    {
+      "source": "/skills/overview",
+      "destination": "/skills/directory"
+    },
+    {
+      "source": "/skills/developers",
+      "destination": "/skills/code-prompts"
+    },
+    {
+      "source": "/skills/teams",
+      "destination": "/skills/platform-prompts"
+    },
+    {
+      "source": "/skills/platform",
+      "destination": "/skills/platform-prompts"
+    },
+    {
+      "source": "/skills/manual",
+      "destination": "/integration/quick-start"
     }
   ]
 }
diff --git a/evaluations/evaluators/overview.mdx b/evaluations/evaluators/overview.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Overview
 description: Understand evaluators - the scoring functions that assess your LLM outputs for quality, safety, and correctness.
 ---
 
+<Tip>
+  **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+</Tip>
+
 Evaluators are scoring functions that assess the quality of your LLM's outputs. They're the building blocks for [experiments](/evaluations/experiments/overview), [online evaluation](/evaluations/online-evaluation/overview), and [guardrails](/evaluations/guardrails/overview).
 
 ## Choose Your Approach

diff --git a/evaluations/experiments/overview.mdx b/evaluations/experiments/overview.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Overview
 description: Run batch tests on your LLM applications to measure quality, compare configurations, and catch regressions before production.
 ---
 
+<Tip>
+  **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+</Tip>
+
 Experiments let you systematically test your LLM applications before deploying to production. Run your prompts, models, or agents against datasets and measure quality with evaluators.
 
 ## What is an Experiment?

diff --git a/evaluations/experiments/sdk.mdx b/evaluations/experiments/sdk.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Via SDK
 description: Run experiments programmatically from notebooks or scripts to batch test your LLM applications.
 ---
 
+<Tip>
+  **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+</Tip>
+
 LangWatch makes it easy to run experiments from code.
 Just add a few lines to start tracking your experiments.
 

diff --git a/evaluations/guardrails/code-integration.mdx b/evaluations/guardrails/code-integration.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Code Integration
 description: Add guardrails to your LLM application to block harmful content in real-time.
 ---
 
+<Tip>
+  **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+</Tip>
+
 This guide shows how to integrate guardrails into your application using the LangWatch SDK. Guardrails run evaluators synchronously and return results you can act on immediately.
 
 ## Basic Usage

diff --git a/evaluations/guardrails/overview.mdx b/evaluations/guardrails/overview.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Overview
 description: Block or modify harmful LLM responses in real-time to enforce safety and policy constraints.
 ---
 
+<Tip>
+  **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+</Tip>
+
 Guardrails are evaluators that run in real-time and **act** on the results - blocking, modifying, or rejecting responses that violate your safety or policy rules. Unlike [monitors](/evaluations/online-evaluation/overview) which only measure and alert, guardrails actively prevent harmful content from reaching users.
 
 ## Guardrails vs Monitors

diff --git a/evaluations/online-evaluation/overview.mdx b/evaluations/online-evaluation/overview.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Overview
 description: Continuously score and monitor your LLM's production traffic for quality and safety with online evaluation.
 ---
 
+<Tip>
+  **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+</Tip>
+
 Online evaluation lets you continuously score your LLM's production traffic. Unlike [experiments](/evaluations/experiments/overview) which test before deployment, online evaluation monitors your live application to catch quality issues, detect regressions, and ensure safety.
 
 <Info>

diff --git a/evaluations/overview.mdx b/evaluations/overview.mdx
@@ -4,6 +4,10 @@ sidebarTitle: Overview
 description: Ensure quality and safety for your LLM applications with experiments, online evaluation, guardrails, and evaluators.
 ---
 
+<Tip>
+  **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+</Tip>
+
 LangWatch provides comprehensive evaluations tools for your LLM applications. Whether you're evaluating before deployment or monitoring in production, we have you covered.
 
 ## The Agent Evaluation Lifecycle

diff --git a/integration/go/guide.mdx b/integration/go/guide.mdx
@@ -7,6 +7,10 @@ keywords: LangWatch, Go, Golang, SDK, integration, guide, setup, tracing, spans,
 
 import LLMsTxtProtip from "/snippets/llms-txt-protip.mdx";
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 <div className="not-prose" style={{display: "flex", gap: "8px", padding: "0"}}>
   <div>
     <a href="https://github.com/langwatch/langwatch/tree/main/sdk-go" target="_blank">

diff --git a/integration/mcp.mdx b/integration/mcp.mdx
@@ -26,10 +26,14 @@ Go to your LangWatch project **Settings** page and copy your API key. The API ke
 <Step title="Configure your MCP">
 
 <Tabs>
-<Tab title="Cursor">
-1. Open Cursor Settings
-2. Navigate to the **Tools and MCP** section in the sidebar
-3. Add the LangWatch MCP server:
+<Tab title="Claude Code">
+Run this command to add the MCP server:
+
+```bash
+claude mcp add langwatch -- npx -y @langwatch/mcp-server --apiKey your-api-key-here
+```
+
+Or add it manually to your `~/.claude.json`:
 
 ```json
 {
@@ -45,16 +49,30 @@ Go to your LangWatch project **Settings** page and copy your API key. The API ke
 }
 ```
 
+See the [Claude Code MCP documentation](https://code.claude.com/docs/en/mcp#plugin-provided-mcp-servers) for more details.
 </Tab>
 
-<Tab title="Claude Code">
-Run this command to add the MCP server:
+<Tab title="Copilot">
+Add to `.vscode/mcp.json` in your project (or use **MCP: Add Server** from the Command Palette):
 
-```bash
-claude mcp add langwatch -- npx -y @langwatch/mcp-server --apiKey your-api-key-here
+```json
+{
+  "servers": {
+    "langwatch": {
+      "type": "stdio",
+      "command": "npx",
+      "args": ["-y", "@langwatch/mcp-server"],
+      "env": { "LANGWATCH_API_KEY": "your-api-key-here" }
+    }
+  }
+}
 ```
+</Tab>
 
-Or add it manually to your `~/.claude.json`:
+<Tab title="Cursor">
+1. Open Cursor Settings
+2. Navigate to the **Tools and MCP** section in the sidebar
+3. Add the LangWatch MCP server:
 
 ```json
 {
@@ -69,12 +87,27 @@ Or add it manually to your `~/.claude.json`:
   }
 }
 ```
+</Tab>
 
-See the [Claude Code MCP documentation](https://code.claude.com/docs/en/mcp#plugin-provided-mcp-servers) for more details.
+<Tab title="ChatGPT">
+1. Go to **Settings → Connectors**
+2. Click **Add connector**
+3. Enter the server URL: `https://mcp.langwatch.ai/sse`
+4. For authentication, select **Bearer Token** and enter your LangWatch API key (get one at [app.langwatch.ai/authorize](https://app.langwatch.ai/authorize))
 
+*Requires a Plus or Team plan.*
 </Tab>
 
-<Tab title="Other Editors">
+<Tab title="Claude Chat">
+1. Go to **Settings → Connectors**
+2. Click **Add custom connector**
+3. Enter the server URL: `https://mcp.langwatch.ai/sse`
+4. Click **Advanced settings**, select **Bearer Token** auth, and enter your LangWatch API key (get one at [app.langwatch.ai/authorize](https://app.langwatch.ai/authorize))
+
+*Requires a Pro or Max plan.*
+</Tab>
+
+<Tab title="Other">
 For other MCP-compatible editors, add the following configuration to your MCP settings file:
 
 ```json
@@ -109,6 +142,13 @@ Open your AI assistant chat (e.g., `Cmd/Ctrl + I` in Cursor, or `Cmd/Ctrl + Shif
 | `LANGWATCH_API_KEY` | `--apiKey` | API key for authentication |
 | `LANGWATCH_ENDPOINT` | `--endpoint` | API endpoint (default: `https://app.langwatch.ai`) |
 
+### Two Modes
+
+The MCP server runs in two modes:
+
+- **Local (stdio)**: Default. Runs as a subprocess of your coding assistant (Claude Code, Copilot, Cursor). API key set via `--apiKey` flag or `LANGWATCH_API_KEY` env var.
+- **Remote (HTTP/SSE)**: For web-based assistants (ChatGPT, Claude Chat). Hosted at `https://mcp.langwatch.ai`. API key sent as `Authorization: Bearer <key>` per session — each user brings their own key.
+
 ## Usage Examples
 
 ### Write Agent Tests with Scenario

diff --git a/integration/python/guide.mdx b/integration/python/guide.mdx
@@ -7,6 +7,10 @@ keywords: LangWatch, Python, SDK, integration, guide, setup, tracing, spans, tra
 
 import LLMsTxtProtip from "/snippets/llms-txt-protip.mdx";
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 <div className="not-prose" style={{display: "flex", gap: "8px", padding: "0"}}>
   <div>
     <a href="https://github.com/langwatch/langwatch/tree/main/python-sdk" target="_blank">

diff --git a/integration/python/integrations/agno.mdx b/integration/python/integrations/agno.mdx
@@ -5,6 +5,10 @@ description: Instrument Agno agents with LangWatch’s Python SDK to send traces
 keywords: agno, openinference, langwatch, python, tracing, observability
 ---
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 LangWatch integrates with Agno through OpenInference instrumentation to capture traces from your Agno agents automatically.
 
 ## Installation

diff --git a/integration/python/integrations/langchain.mdx b/integration/python/integrations/langchain.mdx
@@ -6,6 +6,10 @@ icon: python
 keywords: langchain, instrumentation, callback, langwatch, python, tracing
 ---
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 LangWatch integrates with Langchain to provide detailed observability into your chains, agents, LLM calls, and tool usage.
 
 ## Installation

diff --git a/integration/python/integrations/langgraph.mdx b/integration/python/integrations/langgraph.mdx
@@ -6,6 +6,10 @@ icon: python
 keywords: langgraph, instrumentation, callback, langwatch, python, tracing
 ---
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 LangWatch integrates with LangGraph to provide detailed observability into your graph-based agents, LLM calls, and tool usage.
 
 ## Installation

diff --git a/integration/python/integrations/open-ai.mdx b/integration/python/integrations/open-ai.mdx
@@ -6,6 +6,10 @@ icon: python
 keywords: openai, instrumentation, autotrack, langwatch, python
 ---
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 LangWatch integrates with OpenAI to automatically capture detailed information about your LLM calls.
 
 ## Installation

diff --git a/integration/quick-start.mdx b/integration/quick-start.mdx
@@ -3,6 +3,10 @@ title: Quick Start
 mode: "wide"
 ---
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 LangWatch helps you understand every user interaction (**Thread**), each individual AI task (**Trace**), and all the underlying steps (**Span**) involved. We've made getting started super smooth.
 
 Let's get cracking.

diff --git a/integration/typescript/guide.mdx b/integration/typescript/guide.mdx
@@ -7,6 +7,10 @@ keywords: langwatch, typescript, sdk, guide, observability, tracing, logging, da
 
 import LLMsTxtProtip from "/snippets/llms-txt-protip.mdx";
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 <div className="not-prose" style={{display: "flex", gap: "8px", padding: "0"}}>
   <div>
   <a href="https://github.com/langwatch/langwatch/tree/main/typescript-sdk" target="_blank">

diff --git a/integration/typescript/integrations/langchain.mdx b/integration/typescript/integrations/langchain.mdx
@@ -6,6 +6,10 @@ icon: square-js
 keywords: langchain, instrumentation, callback, langwatch, typescript, tracing
 ---
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 LangWatch integrates with Langchain to provide detailed observability into your chains, agents, LLM calls, and tool usage.
 
 ## Installation

diff --git a/integration/typescript/integrations/mastra.mdx b/integration/typescript/integrations/mastra.mdx
@@ -5,6 +5,10 @@ sidebarTitle: Mastra
 keywords: mastra, langwatch, tracing, observability, typescript, agent framework, ai agents
 ---
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 LangWatch integrates with Mastra through OpenTelemetry to capture traces from your Mastra agents automatically.
 
 ## Installation

diff --git a/integration/typescript/integrations/vercel-ai-sdk.mdx b/integration/typescript/integrations/vercel-ai-sdk.mdx
@@ -7,6 +7,10 @@ keywords: vercel ai sdk, langwatch, tracing, observability, vercel, ai, sdk
 
 import TypeScriptIntro from "/snippets/typescript-intro.mdx";
 
+<Tip>
+  **Quick setup?** Instead of following these steps manually, [copy a prompt](/skills/code-prompts#instrument-my-code) into your coding agent and it will set this up for you automatically.
+</Tip>
+
 <TypeScriptIntro />
 
 ## Installation
-Original file line number
+Diff line change
@@ Expand Up / @@ -4,6 +4,10 @@ sidebarTitle: Overview @@
     description: Continuously score and monitor your LLM's production traffic for quality and safety with online evaluation.
     ---
+    <Tip>
+      **Let your agent set this up.** [Copy the evaluations prompt](/skills/code-prompts#set-up-evaluations) into your coding agent to get started automatically.
+    </Tip>
     Online evaluation lets you continuously score your LLM's production traffic. Unlike [experiments](/evaluations/experiments/overview) which test before deployment, online evaluation monitors your live application to catch quality issues, detect regressions, and ensure safety.
     <Info>
@@ Expand Down @@