# AI-Generated Documentation
When a dataset is first activated, Rasgo AI indexes it and then automatically generates documentation for it. This documentation includes:
* Notes: notes that describe the dataset wholistically such as the nature of the data, its granularity, and potential use cases for it
* Column Descriptions: short descriptions for each column that describe the format of values within the column and what the data indicates
Column descriptions will also have an AI-generated 'status', indicating if AI is confident in its assessment of the data or if it is uncertain. The yellow icon indicates that the AI is uncertain and wants you to modify the column description. Once you do, it will update to green and your column readiness score will improve.
{% hint style="info" %}
You can filter on 'Status': 'Needs Input' to only see columns that you need to review.
{% endhint %}
AI-generated documentation is intended to be a great starting point, but it should not be relied on as 100% accurate :smile:. The best way to use this documentation is to review and update it with additional context that the AI does not have about your business.
## How it Works
1. When a table is activated, Rasgo indexes the schema of the table (table name, column names, and column data types)
2. Rasgo kicks off an AI documentation process for the table
3. The AI documentation process first looks at a short sample of the data for the entire table and generates dataset notes
4. Next, it runs through the columns in chunks and samples values from each column to help write an accurate description for the column
5. Finally, it evaluates its own confidence level in generating the column description to see if it needs further human review
---
# Agent Instructions: 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.rasgoml.com/rasgo-docs/using-rasgo/auto-documentation.md?ask=
```
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.