# 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 [#ai-context](https://docs.usepylon.com/pylon-docs/notebooks/blocks#ai-context "mention") in [notebooks](https://docs.usepylon.com/pylon-docs/account-intelligence/notebooks "mention"). 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.

### Example: Upsell Opportunities Use AI fields to surface upsell signals into a multiselect [custom-fields](https://docs.usepylon.com/pylon-docs/platform/custom-fields "mention") based on a prompt and set of options.

This field is extracting structured data from [#ai-context](https://docs.usepylon.com/pylon-docs/notebooks/blocks#ai-context "mention") in[notebooks](https://docs.usepylon.com/pylon-docs/account-intelligence/notebooks "mention"), 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.