Skip to main content
Answered

Darshan Hiranandani Dubai : Has anyone successfully implemented Fin for acquisition-focused use cases on a website?

  • November 14, 2024
  • 1 reply
  • 3 views

Hi Everyone, I’m Emmanuel Katto from Dubai, Has anyone experimented with using Fin for website conversion use cases, particularly for driving acquisitions on a public website? While Fin’s content understanding is great for support, we’re curious if it could be leveraged to help with lead generation or conversion goals—like booking demos or signing up users—rather than just resolving customer questions. The idea would be to train it on various website pages and PDF content to simplify the process and potentially eliminate the need for managing numerous custom questions. Any thoughts or suggestions on how this could be implemented effectively?

 

Regards

Emmanuel Katto

Best answer by mateusz.leszkiewicz

HI ​@emmanuelkatto24, It’s Mat from the Support Engineering Team 😀
 

Fin can access and interpret information from a public URL, and it should be able to answer questions from a customer that a human teammate would be able to answer while looking at the same information. However, pages with dynamic content, such as a marketing site or an online store, may present challenges because Fin's ability to "read" customer-facing information from a site's HTML is limited. Information in an article format works best for Fin's language model.

To leverage Fin for website conversion use cases, you can re-ingest all of a customer's Fin content from the backend using the "Fin details" admin tool. Ensure that the content is "AVAILABLE" for Fin using the "External content" admin tool. Content that is not readable from the page's HTML, such as content behind a login or in an image, and URLs with a redirect, might not sync properly. It's also important that all articles you want to sync share the same root URL.

For driving acquisitions, you can sync content from a public website by using the most basic URL stem possible to ensure Fin imports and keeps the content updated. Fin syncs with the URL source once a week, but you can manually re-sync to update the content more frequently if needed.

 

View original
Did this topic help you find an answer to your question?

1 reply

mateusz.leszkiewicz
Intercom Team
Forum|alt.badge.img+5

HI ​@emmanuelkatto24, It’s Mat from the Support Engineering Team 😀
 

Fin can access and interpret information from a public URL, and it should be able to answer questions from a customer that a human teammate would be able to answer while looking at the same information. However, pages with dynamic content, such as a marketing site or an online store, may present challenges because Fin's ability to "read" customer-facing information from a site's HTML is limited. Information in an article format works best for Fin's language model.

To leverage Fin for website conversion use cases, you can re-ingest all of a customer's Fin content from the backend using the "Fin details" admin tool. Ensure that the content is "AVAILABLE" for Fin using the "External content" admin tool. Content that is not readable from the page's HTML, such as content behind a login or in an image, and URLs with a redirect, might not sync properly. It's also important that all articles you want to sync share the same root URL.

For driving acquisitions, you can sync content from a public website by using the most basic URL stem possible to ensure Fin imports and keeps the content updated. Fin syncs with the URL source once a week, but you can manually re-sync to update the content more frequently if needed.

 


Cookie policy

We use cookies to enhance and personalize your experience. If you accept you agree to our full cookie policy. Learn more about our cookies.

 
Cookie settings