> For the complete documentation index, see [llms.txt](https://docs.rasgoml.com/rasgo-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.rasgoml.com/rasgo-docs/using-rasgo/ai-notes.md).

# AI Notes

Notes are natural language instructions for the AI agent. 

## Creating Notes

To create a note, click 'Add Note' and then type or paste in your note. Good notes are:

* concise - to conserve tokens
* specific - referencing exact names within the data such as a column name or value within a column
* human understandable - a good sanity check for your note is, "Could an intern that hasn't worked with this data before understand this note?"

<figure><img src="/files/pwXvn6voI1sCLdAlNUUA" alt=""><figcaption><p>AI Manager - Notes Screen</p></figcaption></figure>

Notes can (and often should) be linked to multiple datasets. This allows you to centralize logic for explaining something that applies to multiple datasets in your account.

<figure><img src="/files/Dvmrga511rBzKymI2EfI" alt=""><figcaption><p>Making a note that is linked to multiple datasets</p></figcaption></figure>

## Types of Notes

Notes are classified by AI into 3 categories:

1. Data Lineage - where the data comes from
2. Business Context - explanations of nuances related to your business
3. Semantic Layer - specific column and table relationships such as KPI definitions and join keys

As part of the AI Readiness evaluation, we check for coverage across each of these categories for each AI-visible dataset.

## Example Notes

Here are some example scenarios where you may want to create a note:

#### Explaining an Acronym

Does your organization have a pressing need to abbreviate everything? You're not alone, but this can be confusing for AI. Use Notes to teach AI your acronyms, i.e.:

{% hint style="info" %}
**CACP means Customer Acquisition Cost Payback and is calculated as Sales & Marketing Expenses in Period / (Net New MRR Acquired in Period \* Gross Margin)**
{% endhint %}

#### Directing AI to Choose the Right Table

Do you have tables that look very similar for different business units? You can teach AI which table to use in which scenario with a note, i.e.:

{% hint style="info" %}
**The table prefix "ABC" refers to our alcohol business unit, and "DEF" refers to our diesel fuel business unit**
{% endhint %}


---

# 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 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/ai-notes.md?ask=<question>
```

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.