> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/plugins-and-integrations/convai-unity-sdk/advanced-topics.md).

# Customize and extend the SDK

The Convai Unity SDK works out of the box for most training simulations, interactive experiences, and games. This section covers what to reach for when the defaults do not fit your deployment: replacing built-in providers with custom implementations, diagnosing performance issues with built-in telemetry, and adding custom modules to the runtime.

{% hint style="info" %}
These pages assume C# proficiency and familiarity with Unity's component lifecycle. If you are still setting up your first scene, start with the [Getting Started](/api-docs/plugins-and-integrations/convai-unity-sdk/getting-started.md) section.
{% endhint %}

<table data-view="cards"><thead><tr><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Credentials, identity, and storage</strong><br>Replace the SDK's credential, identity, and persistence systems with your own implementations. Essential for CI pipelines, auth-backed identity, and cloud save integration.</td><td><a href="/pages/RSZXpj40gmNFoKyKxdOV">/pages/RSZXpj40gmNFoKyKxdOV</a></td></tr><tr><td><strong>Logging, metrics, and retry policy</strong><br>Tune log verbosity per subsystem, read server-side pipeline latency metrics, and configure retry behavior for resilient connections.</td><td><a href="/pages/5679714dc01a4244d0d11caee67e8c32da80d5c3">/pages/5679714dc01a4244d0d11caee67e8c32da80d5c3</a></td></tr><tr><td><strong>Runtime module system</strong><br>Understand when to build custom modules, how the module lifecycle works, and which SDK extension points are safe to use.</td><td><a href="/pages/5c7f9583038d0635f6ec4cab5bab3847c7c9e158">/pages/5c7f9583038d0635f6ec4cab5bab3847c7c9e158</a></td></tr></tbody></table>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.convai.com/api-docs/plugins-and-integrations/convai-unity-sdk/advanced-topics.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.