How Pinterest’s User Education team optimizes help center resources while eliminating manual workflows

Customer Stories

background_image background_image


Relying on simple positive/negative article scores and manual processes left the team with little time & direction to focus on servicing the most valuable content. With a 37% year over year increase in monthly active users, Pinterest’s User Education team needed a way to empower users to get the most value out of the product without requiring support assistance. Pinterest’s User Education team partners with Idiomatic to improve the customer experience while reducing contact volume.

Primary Feedback Types

  • Help Center Article Feedback
  • Support


Idiomatic’s Process

  • Create a custom, granular categorization of customer feedback on help center articles.
  • Train machine learning to predict categorizations with accuracy.
  • Customize an insights dashboard to highlight articles with low ratings and unlock insights into article feedback to improve self-service options.


93% positive help center ratings

Pinterest User Education improves the customer experience with product launches by updating content messaging based on real-time insights.

32% decrease in complaints

Pinterest User Education increases help center clarity & accuracy by uncovering the reason behind customer complaints.

6% increase in help center scores

Pinterest User Education prioritizes improvements to help center articles with below average and declining scores.

31% decrease in contacts volume

Pinterest User Education drives down incoming contact volume by creating & adapting help center content to address common questions sent to support.

Help center content

Pinterest User Education optimizes help center resource searchability, organization, & suggestions based on customer language.

“We use Idiomatic ticket data to inform how users talk about certain features and then brought those common words and phrases into the new topics and “subtopics for the Help Center.”

“Every single time I am making an update to a Help Center article, I always check the insights on Idiomatic to see what’s working well and what is helpful, to see what users dislike and what they don’t understand as well as use them to compare user sentiment after I have made an update.”


Using Idiomatic’s analysis of customer feedback to help center articles, the User Education team filtered for the lowest performing articles. With the goal to improve scores for a specific article, the team quantified specific customer questions and points of confusion that a certain article didn’t address. The User Education team updated the article to more clearly answer top related questions. By anticipating customer confusion with Idiomatic’s analysis, the User Education team drives down support contact volume and empowers users.

If you would like to learn how Idiomatic’s solutions can help your company achieve tangible results, request your custom demo today.