> 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/build/understand/explore-data.md).

# Explore data

Inspect the metadata, then the values, before you commit to a source.

Metadata tells you what a dataset claims to be. The values tell you what it actually is. Exploring means checking both before you build on a source, in two places:

* [**Datasets**](https://v2.dataos.info/build/understand/explore-data/datasets.md): the catalog view. Inspect schema, columns, tags, ownership, lineage, and recent query activity. Start here to understand structure and trust.
* [**Workbench**](https://v2.dataos.info/build/understand/explore-data/workbench.md): the query view. Run SQL against the source, preview results, and confirm the values match what the metadata promised.

The order is deliberate. Read the metadata first to decide whether a dataset is worth opening, then validate the data in Workbench before you commit it to a model. A few minutes here saves rework later.

At the end you can answer one question: **is this dataset the right input for my Data Product?** If yes and your engine can reach it, go to [Productize](https://v2.dataos.info/build/productize/overview.md). If yes but it is not reachable, [Move](https://v2.dataos.info/build/move/overview.md) it in. If no, you found out before writing a line of SQL.


---

# 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/build/understand/explore-data.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.
