Disney Streaming Copilot
Improving Content Discovery Through Micro-Interactions.
Disney Streaming Copilot is a personalized virtual assistant for Disney+ users. It generates precise instructions for AI models, resulting in more accurate media suggestions. Users can create a customized environment with their favorite characters and stories, making selecting movies more engaging and tailored through micro-interactions.
Context: 12-Week Exploratory Project
Role: UX Product Designer
Tools: Figma, Adobe Creative Cloud, Blender
Problem: Disney Streaming’s artificial intelligence algorithms are not human-centered.
Opportunity: How might we help users efficiently communicate with AI models to generate personalized outputs?
Solution: A virtual assistant that helps users effectively use AI to provide more targeted content recommendations by leveraging familiar micro-interactions during prompting.
Personalizing Virtual Assistants to Create Familiarity During Content Discovery
Users can customize their Disney+ streaming application environment, displaying the stories and characters they love the most. This creates a sense of familiarity and comfort when navigating Disney's extensive library. 71% of consumers expect companies to deliver personalized interactions. Personalization not only improves performance but also enhances customer outcomes. Companies that grow faster generate 40% more revenue from personalization than their slower-growing counterparts.
An Adaptive Survey That Alters Questions Based On External Conditions, Viewing History, And Online Trends
This survey uses machine learning to adapt the questions displayed based on external factors such as weather, users' viewing history, current pop culture trends, and current moods and preferences. Adaptive questions simplify the search process, eliminating the need for users to query AI models directly. This guided and simplified method allows users to discover relevant content at that moment rather than relying solely on their viewing history. Five results are displayed to prevent users from being overwhelmed by too many choices.
Achieve Customized Media Results Quickly Through Manual Preferences Input
Users can manually input their preferences and parameters into the AI models. This allows them to obtain their desired content quickly without completing a survey each time. They can also utilize results from the last survey, modifying only what needs to be changed. This approach provides users with a focused way to specify their preferences.
Micro-Interactions During Content Discovery Create Magic In Simple Interactions.
First and foremost, Disney is a content company, with technology playing a secondary role. Micro-interactions can create the magical moments currently absent from Disney+. Disney consistently constructs an intriguing world in its various forms of entertainment, be it the hidden Mickeys at its parks or Easter eggs in its media. Implementing micro-interactions in its application can infuse the missing magic and enhance its brand.
Disney+ launched as a digital streaming service
Disney+ launched as a digital streaming service, bringing Disney's magic into homes through one central hub and making its media more accessible than ever. With approximately 164.2 million users, it rapidly became one of the most popular streaming services within a few years of its existence, largely due to its impressive content library.
Disney Streaming’s artificial intelligence algorithms are not human-centered.
Artificial Intelligence (AI) algorithms have been introduced in streaming services like Disney+ to simplify content discovery. However, these algorithms are not entirely user-centric. They base recommendations solely on past data rather than considering the individual's current content preferences. Since AI models for Disney+ primarily serve as a one-way channel for content recommendations, many users are left uncertain about other internal content discovery methods.
I conducted a competitive analysis of Disney+ and its main competitors to identify their market niche and potential strategies for improvement.
My research wasn't limited to streaming services.
I also explored popular AI tools such as ChatGPT, Midjourney, and Grammarly, which have gained significant traction in the mainstream market. Interviewees, especially those from tech, design, and creative sectors, shared their views on this subject. However, individuals less involved in these sectors expressed concerns about the growing influence of AI, primarily due to a lack of understanding of its mechanisms.
How might we help users efficiently communicate with Disney Streaming’s AI models to generate personalized outputs?
Communicating with AI models are intimidating for most casual viewers. By simplifying and providing structure for AI prompting, we aim to make it easier to navigate. Customization helps users focus on the learning journey by making it feel interactive and personalized for casual viewers.
Develop a feature for Disney+ that enables users to interact with AI models directly to enhance content discovery.
After identifying the main concerns with the Disney+ application and streaming services, I focused on developing my insights gathered into wireframes. The ideas focus on segmenting and simplifying how users could prompt AI models to discover content that is relevant to them through an engaged process that is tailor-made for individual users. By using familiar characters, users become more engaged in the process.
After designing version 1.0 of my feature, I sought feedback to iterate.
After presenting my work to interviewees and peers, I identified preferred patterns and potential improvements in information presentation and content discovery. After analyzing the feedback, I focused on specific areas for iterative improvement over subsequent weeks. In two rounds, I updated the user interface and the application's content discovery process to reflect better the feedback received.
My love of movies and technology 🎬 🤝 🚀
Growing up in my immigrant household, communicating with my grandparents wasn’t always easy.
Their English wasn’t excellent, and my Vietnamese/French/Cantonese were even worse. Whether it was a children’s movie like Finding Nemo or a time-period drama, movies were the universal language that brought us together.
Future State
During my research, I found data suggesting users respected what their families, friends, and social media offered. In my next iteration, I would love to look at ways accounts could interact with one another, offering suggestions from the AI model and peers - creating a social element in content discovery.
The Importance of Iteration
With this being a semester-long project, I had plenty of time to go back and look at my work and make continuous improvements over some time. As I looked at my research, I had new moments of clarity, leading me to a final product that I am proud of.
