> For the complete documentation index, see [llms.txt](https://docs.usepylon.com/pylon-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.usepylon.com/pylon-docs/account-intelligence/fields/ai-fields.md).
# AI Fields
Rollup qualitative data onto your account views to quickly assess accounts
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.
### 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.
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.
Prompt for upsell opportunities notebook block
Resulting output for upsell opportunities notebook block
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.usepylon.com/pylon-docs/account-intelligence/fields/ai-fields.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
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.
