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.

You can filter on 'Status': 'Needs Input' to only see columns that you need to review.

AI-generated documentation is intended to be a great starting point, but it should not be relied on as 100% accurate 😄. 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

Last updated