> For the complete documentation index, see [llms.txt](https://docs.corraldata.com/kb/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.corraldata.com/kb/organize-your-data/manage-ai-metadata.md).

# Data Dictionary

Edit descriptions and relationships for tables and columns. This is metadata only - it does not create or change warehouse tables.

When you import your data, we catalog every table and column so AskCorral and the rest of CorralData can understand your warehouse. The Data Dictionary (formerly Manage AI Metadata) collects that catalog in your account so you can review and edit it without digging through the warehouse.

{% @arcade/embed url="<https://app.arcade.software/share/XPnbrovxmzYgRaEmrRJG>" flowId="XPnbrovxmzYgRaEmrRJG" %}

### How it works

1. Open Data Dictionary in the left sidebar.
2. Use Filter Results to filter by Name or Description, then Filter or Clear Filters.
3. Click the pencil Edit on a table to open the edit panel. Update the table Description, each Column description, and optionally mark a column as a Primary key. Table and column physical names are shown for reference and are not editable here.
4. To link a column to another field, turn on Foreign key and choose the target under Select target field…
5. Admins can click Sync Database Schema to refresh the catalog from the current warehouse schema for this account.
6. Use Download: CSV or JSON to export the dictionary.


---

# 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://docs.corraldata.com/kb/organize-your-data/manage-ai-metadata.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.
