feat(agent-insights): product docs (#14148)

Author: obostjancic

docs/platforms/python/integrations/anthropic/index.mdx

@@ -1,15 +1,14 @@
 ---
 title: Anthropic
 description: "Learn about using Sentry for Anthropic."
+sidebar_hidden: true
 ---
 
-<Alert title="Beta">
+<Alert level="info" title="Product compatibility">
 
-The support for **Anthropic** is in its beta phase.
+This integration is designed for legacy [LLM Monitoring](/product/insights/ai/llm-monitoring/) and is not currently compatible with [AI Agents Insights](/product/insights/agents/).
 
-We are working on supporting different AI libraries (see [GitHub discussion](https://github.com/getsentry/sentry-python/discussions/3007)).
-
-If you want to try the beta features and are willing to give feedback, please let us know on [Discord](https://discord.com/invite/Ww9hbqr).
+We are working on this, and it will soon be compatible with [AI Agents Insights](/product/insights/agents/).
 
 </Alert>
 

docs/platforms/python/integrations/cohere/index.mdx

@@ -1,18 +1,18 @@
 ---
 title: Cohere
 description: "Learn about using Sentry for Cohere."
+sidebar_hidden: true
 ---
 
-<Alert title="Beta">
+<Alert level="info" title="Product compatibility">
 
-The support for **Cohere** is in its beta phase.
+This integration is designed for legacy [LLM Monitoring](/product/insights/ai/llm-monitoring/) and is not currently compatible with [AI Agents Insights](/product/insights/agents/).
 
-We are working on supporting different AI libraries (see [GitHub discussion](https://github.com/getsentry/sentry-python/discussions/3007)).
-
-If you want to try the beta features and are willing to give feedback, please let us know on [Discord](https://discord.com/invite/Ww9hbqr).
+We are working on this, and it will soon be compatible with [AI Agents Insights](/product/insights/agents/).
 
 </Alert>
 
+
 This integration connects Sentry with the [Cohere Python SDK](https://github.com/cohere-ai/cohere-python).
 The integration has been confirmed to work with Cohere 5.3.3.
 

docs/platforms/python/integrations/huggingface_hub/index.mdx

@@ -1,15 +1,14 @@
 ---
 title: Huggingface Hub
 description: "Learn about using Sentry for Huggingface Hub."
+sidebar_hidden: true
 ---
 
-<Alert title="Beta">
+<Alert level="info" title="Product compatibility">
 
-The support for **Huggingface Hub** is in its beta phase.
+This integration is designed for legacy [LLM Monitoring](/product/insights/ai/llm-monitoring/) and is not currently compatible with [AI Agents Insights](/product/insights/agents/).
 
-We are working on supporting different AI libraries (see [GitHub discussion](https://github.com/getsentry/sentry-python/discussions/3007)).
-
-If you want to try the beta features and are willing to give feedback, please let us know on [Discord](https://discord.com/invite/Ww9hbqr).
+We are working on this, and it will soon be compatible with [AI Agents Insights](/product/insights/agents/).
 
 </Alert>
 
@@ -26,6 +25,7 @@ Install `sentry-sdk` from PyPI with the `huggingface_hub` extra:
 ```bash {tabTitle:pip}
 pip install "sentry-sdk[huggingface_hub]"
 ```
+
 ```bash {tabTitle:uv}
 uv add "sentry-sdk[huggingface_hub]"
 ```

docs/platforms/python/integrations/langchain/index.mdx

@@ -1,18 +1,18 @@
 ---
 title: Langchain
 description: "Learn about using Sentry for Langchain."
+sidebar_hidden: true
 ---
 
-<Alert title="Beta">
+<Alert level="info" title="Product compatibility">
 
-The support for **LangChain** is in its beta phase.
+This integration is designed for legacy [LLM Monitoring](/product/insights/ai/llm-monitoring/) and is not currently compatible with [AI Agents Insights](/product/insights/agents/).
 
-We are working on supporting different AI libraries (see [GitHub discussion](https://github.com/getsentry/sentry-python/discussions/3007)).
-
-If you want to try the beta features and are willing to give feedback, please let us know on [Discord](https://discord.com/invite/Ww9hbqr).
+We are working on this, and it will soon be compatible with [AI Agents Insights](/product/insights/agents/).
 
 </Alert>
 
+
 This integration connects Sentry with [Langchain](https://github.com/langchain-ai/langchain).
 The integration has been confirmed to work with Langchain 0.1.11.
 

docs/platforms/python/integrations/openai/index.mdx

@@ -1,15 +1,14 @@
 ---
 title: OpenAI
 description: "Learn about using Sentry for OpenAI."
+sidebar_hidden: true
 ---
 
-<Alert title="Beta">
+<Alert level="info" title="Product compatibility">
 
-The support for **OpenAI** is in its beta phase.
+This integration is designed for legacy [LLM Monitoring](/product/insights/ai/llm-monitoring/) and is not currently compatible with [AI Agents Insights](/product/insights/agents/).
 
-We are working on supporting different AI libraries (see [GitHub discussion](https://github.com/getsentry/sentry-python/discussions/3007)).
-
-If you want to try the beta features and are willing to give feedback, please let us know on [Discord](https://discord.com/invite/Ww9hbqr).
+We are working on this, and it will soon be compatible with [AI Agents Insights](/product/insights/agents/).
 
 </Alert>
 
@@ -27,6 +26,7 @@ Install `sentry-sdk` from PyPI with the `openai` extra:
 ```bash {tabTitle:pip}
 pip install "sentry-sdk[openai]"
 ```
+
 ```bash {tabTitle:uv}
 uv add "sentry-sdk[openai]"
 ```
@@ -43,7 +43,6 @@ An additional dependency, `tiktoken`, is required if you want to calculate token
 
 Verify that the integration works by creating an AI pipeline. The resulting data should show up in your LLM monitoring dashboard.
 
-
 ```python
 import sentry_sdk
 from sentry_sdk.ai.monitoring import ai_track
@@ -115,7 +114,6 @@ You can pass the following keyword arguments to `OpenAIIntegration()`:
 
   The default is `None`.
 
-
 ## Supported Versions
 
 - OpenAI: 1.0+

docs/product/insights/agents/dashboard.mdx

@@ -0,0 +1,67 @@
+---
+title: AI Agents Dashboard
+sidebar_order: 10
+description: "Learn how to use Sentry's AI Agents Dashboard."
+---
+
+<Include name="feature-limited-on-team-retention.mdx" />
+
+Once you've [configured the Sentry SDK](/product/insights/agents/getting-started/) for your AI agent project, you'll start receiving data in the Sentry [AI Agents Insights](https://sentry.io/orgredirect/organizations/:orgslug/insights/agents/) dashboard.
+
+The main dashboard provides a comprehensive view of all your AI agent activities, performance metrics, and recent executions.
+
+![AI Agents Monitoring Overview](./img/overview.png)
+
+The dashboard displays key widgets like:
+
+- **Traffic**: Shows agent runs over time, error rates, and releases to track overall activity and health
+- **Duration**: Displays response times for your agent executions to monitor performance
+- **Recommended Issues**: Highlights recent errors and problems that need attention, including agent failures and exceptions
+- **LLM Generations**: Shows the number of language model calls with breakdowns by specific models (claude, 4o-mini, etc.)
+- **Tool Usage**: Shows which tools your agents use most frequently
+- **Token Usage**: Tracks token consumption over time with breakdown by model
+
+Underneath these widgets are tables that allow you to view data in more detail:
+
+- **Traces**: Recent agent runs with duration, errors, number of LLM and tool calls and token usage
+- **Models**: Traffic, duration, token usage and errors grouped by model
+- **Tools**: Number of requests and their usual durations grouped by tool
+
+![AI Agent Trace Table](./img/trace-table.png)
+
+Click on any trace to open the abbreviated trace view in a drawer.
+
+## Abbreviated Trace View
+
+Opens as a drawer when clicking any trace, showing essential details:
+
+![AI Agent Abbreviated Trace View](./img/abbreviated-trace-view.png)
+
+- **Agent Invocations**: Each agent execution and nested calls
+- **LLM Generations**: Language model interactions with token breakdown
+- **Tool Calls**: External API calls with inputs and outputs
+- **Handoffs**: Agent-to-agent transitions and human handoffs
+- **Critical Timing**: Duration metrics for each step
+- **Errors**: Any failures that occurred
+
+Click **"View in full trace"** for comprehensive debugging details.
+
+## Detailed Trace View
+
+Shows complete agent workflow with full context:
+
+![AI Agent Detailed Trace View](./img/trace-view.png)
+
+This detailed view reveals:
+
+- **Complete Agent Flow**: Every step from initial request to final response
+- **Tool Calls**: When and how the agent used external tools or APIs
+- **Model Interactions**: All LLM calls with prompts and responses (if PII is enabled)
+- **Timing Breakdown**: Duration of each step in the agent workflow
+- **Error Context**: Detailed information about any failures or issues
+
+When your AI agents are part of larger applications (like web servers or APIs), the trace view will include context from other Sentry integrations, giving you a complete picture of how your agents fit into your overall application architecture.
+
+<Alert title="Agent Pipelines vs Direct LLM Calls">
+
+</Alert>

docs/product/insights/agents/getting-started.mdx

@@ -0,0 +1,187 @@
+---
+title: Set Up
+sidebar_order: 0
+description: "Learn how to set up Sentry AI Agent Monitoring"
+---
+
+Sentry AI Agent Monitoring helps you track and debug AI agent applications using our supported SDKs and integrations. Monitor your complete agent workflows from user interaction to final response, including tool calls, model interactions, and custom logic.
+
+To start sending AI agent data to Sentry, make sure you've created a Sentry project for your AI-enabled repository and follow one of the guides below:
+
+## Supported SDKs
+
+### JavaScript - Vercel AI SDK
+
+The Sentry JavaScript SDK supports AI agent monitoring through the Vercel AI integration, which works with Node.js and Bun runtimes. This integration automatically captures spans for your AI agent workflows using the AI SDK's built-in telemetry.
+
+#### Supported Platforms
+
+- <LinkWithPlatformIcon
+    platform="javascript.node"
+    label="Node.js"
+    url="/platforms/javascript/guides/node/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.nextjs"
+    label="Next.js"
+    url="/platforms/javascript/guides/nextjs/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.sveltekit"
+    label="SvelteKit"
+    url="/platforms/javascript/guides/sveltekit/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.nuxt"
+    label="Nuxt"
+    url="/platforms/javascript/guides/nuxt/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.astro"
+    label="Astro"
+    url="/platforms/javascript/guides/astro/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.remix"
+    label="Remix"
+    url="/platforms/javascript/guides/remix/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.solidstart"
+    label="SolidStart"
+    url="/platforms/javascript/guides/solidstart/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.express"
+    label="Express"
+    url="/platforms/javascript/guides/express/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.fastify"
+    label="Fastify"
+    url="/platforms/javascript/guides/fastify/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.nestjs"
+    label="Nest.js"
+    url="/platforms/javascript/guides/nestjs/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.hapi"
+    label="Hapi"
+    url="/platforms/javascript/guides/hapi/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.koa"
+    label="Koa"
+    url="/platforms/javascript/guides/koa/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.connect"
+    label="Connect"
+    url="/platforms/javascript/guides/connect/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.hono"
+    label="Hono"
+    url="/platforms/javascript/guides/hono/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.bun"
+    label="Bun"
+    url="/platforms/javascript/guides/bun/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.aws-lambda"
+    label="AWS Lambda"
+    url="/platforms/javascript/guides/aws-lambda/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.azure-functions"
+    label="Azure Functions"
+    url="/platforms/javascript/guides/azure-functions/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.gcp-functions"
+    label="Google Cloud Functions"
+    url="/platforms/javascript/guides/gcp-functions/configuration/integrations/vercelai/"
+  />
+- <LinkWithPlatformIcon
+    platform="javascript.electron"
+    label="Electron"
+    url="/platforms/javascript/guides/electron/configuration/integrations/vercelai/"
+  />
+
+#### Quick Start with Vercel AI SDK
+
+```javascript
+import { Sentry } from "@sentry/node";
+import { generateText } from "ai";
+import { openai } from "@ai-sdk/openai";
+
+Sentry.init({
+  tracesSampleRate: 1.0,
+  integrations: [
+    Sentry.vercelAIIntegration({
+      recordInputs: true,
+      recordOutputs: true,
+    }),
+  ],
+});
+
+// Your AI agent function
+async function aiAgent(userQuery) {
+  const result = await generateText({
+    model: openai("gpt-4o"),
+    prompt: userQuery,
+    experimental_telemetry: {
+      isEnabled: true,
+      functionId: "ai-agent-main",
+    },
+  });
+
+  return result.text;
+}
+```
+
+### Python - OpenAI Agents
+
+The Sentry Python SDK supports OpenAI Agents SDK.
+
+#### Quick Start with OpenAI Agents
+
+```python
+import sentry_sdk
+from sentry_sdk.integrations.openai_agents import OpenAIAgentsIntegration
+import agents
+from pydantic import BaseModel
+
+sentry_sdk.init(
+    dsn="YOUR_DSN",
+    traces_sample_rate=1.0,
+    send_default_pii=True,  # Include LLM inputs/outputs
+    integrations=[
+        OpenAIAgentsIntegration(),
+    ],
+)
+
+# Create your AI agent
+my_agent = agents.Agent(
+    name="My Agent",
+    instructions="You are a helpful assistant.",
+    model="gpt-4o-mini",
+)
+
+# Your AI agent function
+result = await agents.Runner.run(
+    my_agent,
+    input=user_query,
+)
+
+```
+
+<Alert title="Don't see your platform?">
+
+We'll be adding AI agent integrations continuously. You can also instrument AI agents manually by following our [manual instrumentation guide](/platforms/python/tracing/instrumentation/custom-instrumentation/ai-agents-module).
+
+</Alert>