> For the complete documentation index, see [llms.txt](https://docs.sharinpix.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sharinpix.com/forms/overview-and-getting-started/generate-forms-with-ai.md).
# Generate Forms with AI
This document explains how to use the built-in AI feature in the SharinPix Form Template Builder to generate forms. You can use the AI chat interface to describe the form you want with a prompt, or upload a sample file, such as an image or PDF, from which the form can be generated.
You can generate a form by entering a prompt in the AI chat interface and optionally uploading sample files such as images or PDFs. The AI then uses that input to generate an initial draft of the form.
### How it works
1. Click on "Work with AI".
2. Enter a short description of the form you want.
3. Attach images or PDF files if you have them.
4. Generate the form.
5. Review and update the result if needed.
### Example prompt
> Create a vendor registration form based on the attached PDF.\
> Keep the same sections and fields, use clear labels, and include the checkboxes and text areas as form fields.\
> Mark the required fields as mandatory.
### Example PDF
### Example output
{% hint style="warning" %}
**Note:**
* The generated form is a draft.
* Review the form before using it.
* Clear prompts and clear files usually give better results.
{% endhint %}
{% hint style="info" %}
This feature uses **OpenAI**. If you would like to use another service or model, please contact ****.
{% 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://docs.sharinpix.com/forms/overview-and-getting-started/generate-forms-with-ai.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.
