Internet Browsing AI Models

💡 This feature is still in Beta

Feedback is helpful as we improve the application. New features like this are the product of collaboration with customers like you. If you have any feedback, please reach out!

Note: Website availability

Some websites that require user log in, like LinkedIn, may not be available for browsing due to limits on what non users can access.

In addition to its core functions, you can use PromptLoop to complete requests using internet browsing for context.

While PromptLoop Inference can infer answers based on context, if you need facts or current statistics then the internet is your best source. PromptLoop automatically locates and gathers information from the web.

Because PromptLoop is browsing and processing web results, the formula will be slower than for other functions.

If no results are found or the model is unable to reach a site, it will return "No Results".

Search and Discovery

Use the PROMPTLOOP formula to take an input, such as a ( company name ), to obtain a high level overview/description of each company in each row. You can add additional search terms like ( name of CEO ) to return the name of the CEO of the company for each new cell/row.

Web Browsing

=PROMPTLOOP_BROWSER( search_input, optional_additional_input )

Ex: =PROMPTLOOP_BROWSER( Microsoft, CEO )

Search

The Web browsing function can also accepts correct URLs for websites. This is limited by the same constraints as the general case.

Categorization

Web Browsing

=PROMPTLOOP_BROWSER( search_input (as url link), optional_additional_input )

Ex: =PROMPTLOOP_BROWSER( https://en.wikipedia.org/wiki/Empire_State_Building, height )

Usage and Notes

PromptLoop browsing uses an AI driven agent to find and gather information from the web. This uses credits slightly differently than other functions do.

⏰ Browsing is slower than other functions

Browsing and processing web results takes time, and the formula will be slower than for other functions.

Browsing calls account for a minimum of 50 credits per cell/row and increases depending on the number of pages or results needed to look for the answer.