# AI Fields

AI fields allow you to rollup qualitative insights into structured fields and provide **explainability** for account signals. AI fields can be any data type and can be prompted to look through particular data, most commonly [Blocks](/pylon-docs/account-intelligence/notebooks/blocks.md#ai-context) in [Notebooks](/pylon-docs/account-intelligence/notebooks.md). AI fields can draw from context in any communication source, call recordings, CRM data fields, and much more.

{% hint style="info" %}
Fields are fully customizable based on your use case!
{% endhint %}

### Example: Low Sentiment

For example, rollup a "Low Sentiment" field on accounts into a True/False value to use in calculations, and also surface the reason the customer has low sentiment.

<figure><img src="/files/VZhJ3VEasHrAuVXcQWlS" alt=""><figcaption></figcaption></figure>

### Example: Upsell Opportunities

Use AI fields to surface upsell signals into a multiselect [Custom Fields](/pylon-docs/platform/custom-fields.md) based on a prompt and set of options.

<figure><img src="/files/H3y9hgQQNttxI1GmOCMu" alt="" width="375"><figcaption></figcaption></figure>

This field is extracting structured data from [Blocks](/pylon-docs/account-intelligence/notebooks/blocks.md#ai-context) in[Notebooks](/pylon-docs/account-intelligence/notebooks.md), which has its own prompt. It interprets and structures the data into a field that can now be filtered on and used in views, triggers, etc.

<figure><img src="/files/fOZJBjD5SHaFegcfKHgL" alt=""><figcaption><p>Prompt for upsell opportunities notebook block</p></figcaption></figure>

<figure><img src="/files/2ESbjh0yRCT1DszbR76x" alt=""><figcaption><p>Resulting output for upsell opportunities notebook block</p></figcaption></figure>


---

# 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.usepylon.com/pylon-docs/account-intelligence/fields/ai-fields.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.