Siri AI
Role //
Product Designer, Frontend Developer
Duration //
Jan 2025 - Present
In this project, I look at how generative AI can improve CUI (Conversational User Interface) interactions, specifically Siri.
This is an ongoing project, check again soon for more details!
Problem Space
Currently, CUIs struggle with handling non-command user requests. When faced with such inputs, their responses are often no more advanced than a standard online search, providing results similar to what a human could find independently.
This presents an opportunity for generative AI to offer users actionable insights and tailored responses beyond simple search results.
Command prompts for Siri
Use Cases
With this, there are three use cases that I want to explore:
01: Multi-App Experiences
Generating tailored advice, which populates the appropriate apps.
For example, when learning to bake a cake, Siri places a recipe in the Notes App, a series of timers for scheduling in the Timer App, and a cooking playlist in Spotify.
Mini-App Journey
Interactive Dashboard
I wanted users to interact dynamically with the generated content, enabling actions like regenerating, editing, and rearranging it to refine responses.
Tiles For Different Apps
Tile Layout
Prototyping
To start the project, I began by exploring the capabilities of generative AI, experimenting with various prompts to generate the most detailed responses. I developed the following prototypes to understand how to integrate a generative AI tool with the fronten using Next.js and the OpenAI API.
01: Event Generation
I started by experimenting with how well the OpenAI API could generate steps and action items.
Event Generation Prototypes
02: Grouping and Organizing Content
I then moved to exploring how the OpenAI API can help with organizing and grouping the generated information into a left, middle, and right column.
Tiling prototype when asked to bake a cake
03: Regeneration
When prototyping for regeneration, I thought about how users currently interact with Generative AI tools. I played around with cases where users would want to:
1. Completely change the generated content
2. Add/Remove from the generated content
With a bit of prompt engineering here is the end result:
Regeration protype when asked to change directions and add
More to come soon!