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

02: Sendable Mini-Experiences

Generating mini-experiences that can be sent through iMessage. I aim to explore how to capture the essence of the recipient in the generated experience.

For example, sending grandma a walkthrough of how to use iMessage. How can she feel that it is her grandchild walking her through the experience, and not Siri?

Multi-App Journey

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 frontend.

Prototyping with Next.js and the OpenAI API

More to come soon!