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

# Getting Started

> Choose the right Xenovia integration path and prepare your first governed workflow.

Most teams start in **proxy mode** because it gives immediate coverage with the smallest code change. Use **SDK mode** when you also need policy enforcement around actions that happen after the model call.

## Choose your integration path

| Path           | Best for                                                                                                 | First change                                  |
| -------------- | -------------------------------------------------------------------------------------------------------- | --------------------------------------------- |
| **Proxy mode** | OpenAI SDK, LangChain, LlamaIndex, Vercel AI SDK, Agents SDK, CrewAI, and most OpenAI-compatible clients | Change `base_url` to your Xenovia proxy URL   |
| **SDK mode**   | Tool calls, API requests, writes, file operations, or business actions outside the LLM request           | Add `xenovia.execute()` or `@xenovia.guard()` |

You can use both together: proxy mode for the model layer, SDK mode for downstream side effects.

## Prerequisites

**For proxy mode**

* A Xenovia account and workspace with at least one proxy created.
* Your proxy ID (found under **Proxies** in the platform).
* A Xenovia API key (`xe_...`) scoped to that proxy.
* An LLM client or framework (OpenAI SDK, LangChain, LlamaIndex, Vercel AI SDK, etc.).

**For SDK mode**

* Python ≥ 3.9.
* A Xenovia API key.
* Your agent or tool functions that need policy gating.

## What to decide before rollout

* Which workflow should be governed first
* Which environment to start in `dev` or `staging`, not production
* What should be blocked, redacted, or escalated first
* Which metadata you want attached to traces: environment, user tier, feature, or workflow ID

## Proxy URL format

Every proxy exposes an OpenAI-compatible base URL:

```text theme={null}
https://runtime.xenovia.io/a/{proxy_id}/openai/v1
```

Point your client here and pass the `xe_...` key as the API key. Xenovia resolves the upstream provider credentials server-side.

## Recommended rollout

<Steps>
  <Step title="Create one proxy">
    Give it a clear owner, environment label, and scope so the traces mean something on day one.
  </Step>

  <Step title="Route one workflow">
    Start with a narrow path such as one chat endpoint, one agent runner, or one background job.
  </Step>

  <Step title="Verify trace headers">
    Confirm `X-Xenovia-Session-Id` and `X-Xenovia-Trace-Id` show up in responses and traces land in the platform.
  </Step>

  <Step title="Attach one simple policy">
    Begin with a concrete rule such as blocking a destructive tool or redacting email addresses.
  </Step>

  <Step title="Expand based on evidence">
    Use real traces to add stricter rules, intent checks, and downstream SDK guards.
  </Step>
</Steps>

## Session tracking

Xenovia resolves a session automatically, but for multi-turn agents you should usually pass an explicit `X-Xenovia-Session-Id` header so related calls stay grouped in Traces.

Continue to [Quickstart](/getting-started/quickstart) to run your first proxied call with policy enforcement.