> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/references/readme.md).

# DataOS Reference

The full reference layer of DataOS: per-engine manuals, complete DataOS resource syntax, and interface specifications.

References holds the full technical detail behind DataOS: the full per-engine manuals, the complete syntax for every DataOS resource, and the interface specifications. Where Build and Consume show you how to do a task, References is what those pages link out to when you need the depth; each fact lives here once.

Use References when a task page sends you here for the full detail, or when you already know what you need and want the reference directly.

## What is here

<table data-view="cards"><thead><tr><th></th><th data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>Engine guide</strong><br>The full technical manual for each engine you build Data Products on. Covers connection, permissions, materialization internals, local development, tuning, and failure modes.</td><td><a href="/references/engine-guide/engine-guide.md">Overview</a></td></tr><tr><td><strong>DataOS Resources</strong><br>The complete reference for every resource. Includes Vulcan, Nilus, Lakehouse, Minerva, Secret, Depot, and the rest.</td><td><a href="/references/resources/overview.md">Overview</a></td></tr><tr><td><strong>Interfaces</strong><br>The ways to reach a Data Product, including APIs, BI tools, database clients, AI activation, and the CLI.</td><td><a href="/references/interfaces/overview.md">Overview</a></td></tr></tbody></table>

If you are new to building or consuming, start in [Build](https://v2.dataos.info/build) or [Consume](https://v2.dataos.info/consume); they bring you here when you need the underlying detail.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://v2.dataos.info/references/readme.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.