> For the complete documentation index, see [llms.txt](https://docs.feathery.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.feathery.io/platform/document-intelligence/prompting-guide.md).

# Prompting Guide

To improve the precision and accuracy of your document extractions, you should follow best practices when constructing your document queries. If you want more specific guidance, feel free to reach out in our [community](https://community.feathery.io).

1. Be precise and descriptive with your phrasing. If you're looking for transaction line items on a bank statement, is there any additional context that would be helpful to add? Are there specific items you're looking for, or is it typically part of a specific table? If you're looking for holdings, are you looking for stock, options, cash, or all of the above?
2. Minimize the amount of inference that the AI model needs to do that can instead be part of post-extraction logic. Document Intelligence is great at reading documents, not extrapolating from them.
   1. For example, if you need to find the sum of value A and value B on a document, you shouldn't ask for the sum directly. You should ask separately for value A and value B, and then add the two values together in the post-extraction logic rule.


---

# 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.feathery.io/platform/document-intelligence/prompting-guide.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.