> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agnost.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Quickstart

> Send your first AI interaction to Agnost AI

Use this page to get one tool invocation or AI interaction visible in the [Agnost dashboard](https://app.agnost.ai). The Agnost AI skill detects the right integration route and applies the smallest matching change.

## 1. Get your organization ID

1. Sign in at [app.agnost.ai](https://app.agnost.ai).
2. Open **Settings > Organization**. Copy your organization ID: it's a UUID.

This ID is what we'll refer to as your `org_id` or `AGNOST_ORG_ID` (also called `write_key` in some SDKs). Treat it as a public identifier: it routes telemetry to your workspace, but it does not grant dashboard read access on its own.

<Note>
  If your conversations can contain personal or sensitive data, read [Data Governance](/data-governance) before sending production traffic. Agnost does not currently provide automatic PII redaction before ingestion, so redact or pseudonymize sensitive fields in your application first.
</Note>

<a id="2-pick-a-path" />

## 2. Proceed with skill-based onboarding

Install the skill in your agent environment:

```bash theme={null}
npx skills add AgnostAI/skills --skill agnost-ai
```

Then ask your coding agent to use it from your app root:

```text theme={null}
Use the agnost-ai skill to add Agnost analytics.
Org ID: your-org-id
Target app: .
Verification: local app
Entrypoint: the real chat route, agent call, MCP server startup, or tool call
```

The skill asks for missing facts, detects whether your app needs SDK, MCP, or OpenTelemetry instrumentation, and keeps input/output capture enabled unless you ask to redact it.

After the edit, restart or deploy your app, trigger one real chat, agent action, or MCP tool call, then confirm the event in the dashboard.

***

## Integration guides

Use these guides if you want to wire Agnost yourself or review what the skill will detect.

<CardGroup cols={2}>
  <Card title="AI conversations" icon="message" href="/conversational-overview">
    Track LLM calls and agent turns directly from Python or TypeScript application code.
  </Card>

  <Card title="OpenTelemetry" icon="bolt" href="/otel">
    Forward traces from OTel-enabled frameworks such as Vercel AI SDK, Mastra, LangChain, OpenAI, etc.
  </Card>

  <Card title="MCP servers" icon="wrench" href="/mcp-overview">
    Track tool, resource, and prompt calls from a dedicated MCP server.
  </Card>

  <Card title="MCP Toolbox" icon="database" href="/mcp-toolbox">
    Send telemetry from Google's MCP Toolbox for Databases.
  </Card>
</CardGroup>

***

## Verify

Open [app.agnost.ai](https://app.agnost.ai) and check:

* **Conversations** for SDK-tracked interactions
* **Tools** for MCP tool invocations
* **Raw logs** for the unfiltered event stream

Events usually appear within a few seconds. Nothing showing up? Check the org ID, restart/deploy state, and whether the real app path was exercised.

## Next steps

* [SDK index](/sdks): published packages and imports.
* [Authentication](/authentication): API keys and JWT for dashboard APIs.
* [Data Governance](/data-governance): production data handling.