Quickplay - Curator Assistant
Category Streaming
Accenture finds that 72% of consumers “report frustration at finding something to watch,” up six percentage points from the previous year. Quickplay is addressing the issue head-on with its Curator Assistant tool that combines generative AI with its cloud-native, open platform to shorten the frustration of search and discovery, and to increase the enjoyment of viewing.
Curator Assistant empowers programmers to quickly build storefront rails that contain more titles that match consumer interest and can be programmed more quickly. Using Curator Assistant, content programming teams can create, for example, a Valentine’s Day-themed movie rail that would include not only Valentine’s Day-related films and other romantic-titles but also other films that contain romantic themes or subplots.
Working within the CMS, Curator Assistant uses a natural language interface for assisted discovery, including catalog browsing, filtering, and cross-referencing assets. It also augments content metadata with additional insights, including micro-genre descriptors, emotional tags, and embeddings to strengthen results. It is also capable of determining natural content breakpoints to identify binge markers and ad-breaks that can improve usability and expand monetization opportunities. The solution can also auto-generate content rails based on results extracted from the catalog and further refine the results based on a variety of engagement metrics, enabling programmers to personalize content rails based on individual taste preferences, content analyses, and consumption patterns.
Quickplay’s cloud-native CMS is a critical element in the successful creation and execution of Curator Assistant allowing it to integrate LLMs with a CMS which offers a dramatic improvement over legacy media discovery systems. Because LLMs are trained on a massive amount of data, including public information, they are better at understanding what people are searching for, even if they use conversational language. And they can tap into public datasets to make recommendations based on trends and cultural context to enhance the media metadata available in a CMS.
By applying powerful LLMs to the CMS, Quickplay’s Curator Assistant can provide recommendations that continuously learn from user interactions and reflect viewers’ changing habits and preferences. Further, the CMS ensures compliance standards are met so that users don’t receive recommendations that violate licensing agreements or regional restrictions, and it ensures data privacy guidelines with respect to user data are met as well.
