> 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/web-research.md).

# Web Research

Account Web Research allows you to automatically gather information about your customers from live online sources, including funding rounds, industry news, company press releases, and more. You can leverage Web Research via Account Custom Fields. Web Research fields can be customized by including a custom JSON Schema.

<figure><img src="/files/h6CP1JNJjUSviN5v8BdO" alt="" width="375"><figcaption></figcaption></figure>

#### Description&#x20;

&#x20;Allows you to enter a description to help members and AI identify this field. Ex. "Recent Funding"

<figure><img src="/files/0qluAPdrD7jXM2HqyBN9" alt="" width="362"><figcaption></figcaption></figure>

#### Research Instructions&#x20;

Here you can prompt AI on how to collect the information and what context it should use. Inject variables into your prompt with the `{` key.

<figure><img src="/files/juDF7gy4SoHYNTKTDx0B" alt="" width="365"><figcaption></figcaption></figure>

#### Templates

Research faster using AI web research templates: Latest Funding Round, Company Details, and Recently Acquired.

#### JSON Schema&#x20;

Specify the type of data you want to retreive and the shape of the result. You can then access these retrieved fields in other custom fields.

```
{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "The name of the company"
    },
    "employee_count": {
      "type": "number",
      "description": "The number of employees in the company"
    }
  }
}
```

<figure><img src="/files/btIFZknBm4tSNgt1fa8r" alt="" width="368"><figcaption></figcaption></figure>

### Example: Customer Details

<figure><img src="/files/p89AkcVxDwL6BJEROt1W" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/BfZpEnPDlPhBy4knVtrw" alt=""><figcaption></figcaption></figure>

**JSON Schema:**&#x20;

```
{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "description": "The name of the company"
    },
    "employee_count": {
      "type": "number",
      "description": "The number of employees in the company"
    }
  }
}
```


---

# 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.usepylon.com/pylon-docs/account-intelligence/fields/web-research.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.