How are Generative User Interfaces created?

Generative UI leverages large language models (LLMs), design systems and dynamic templates to transform intent into an accurate visual outcome.

Oscar de la Hera Gomez
Written by Oscar de la Hera Gomez
First published on 08/01/2024 at 15:46
Last Updated on 08/08/2024 at 12:48
<p>A flower that represents Digital Craft with the text "Generative User Interfaces" beneath it.</p>

Generative UI leverages large language models (LLMs), design systems and dynamic templates to transform intent into an accurate visual outcome.

SubscribeWhat are Generative User Interfaces?

Please note that since releasing this article, the following events, advancements and updates have occured:

These updates have been included in the latest version of this article.

In 2024, Generative UI, or GenUI, is considered the future of interfaces and is currently best demonstrated by Brain.ai's Natural AI (video above) or Google Gemini (video below).

The way that systems (i.e. apps or websites) produce Generative UI is as follows:

<p>A diagram that shows how Generative UI is constructed. I starts with a user inputting a multimodal prompt. This prompt is passed on to an AI agent that determines the intent, queries a database and from it returns structured data to a website or app. The website or app then uses this data to construct a layout from a dynamic template.</p>

A user sends a multimodal prompt to an LLM powered AI agent which determines the users intent and queries a database to gather the required data.

The AI agent then transforms the data gathered from the database into an format, known as a structured output, which can be consumed by a dynamic template, producing a user interface which meets the request of the user.

OpenAI: Introducing Structured Outputs in the APIWhat is a Dynamic Template?

To share a separate example of how Generative UI could help a business is the following: 

Consider a customer searching for sneakers on Nike.com. 

  • As the customer browses Nike.com, they force press a UI element that represents a sneaker that they are interested in.
  • This process activates a microphone function that allows the customer speaks to their smartphone. 
  • The customer asks Nike.com to find an outfit that matches this shoe.
  • The AI agent takes the multimodal intent (i.e. "Find an out fit for this shoe" along with the shoe data) and returns an interface with outfits that the user might like.

Looking to learn more about design and technology?

Search our blog to discover more content and tutorials on design and technology.

Search our Blog

Any Questions?

We are actively looking for feedback on how to improve this resource. Please send us a note to inquiries@delasign.com with any thoughts or feedback you may have.
SubscribeContact UsVisit our BlogView our ServicesView our Work

Partner with us

We would love to get to know you and see how we can help your organization with its goals and needs.
Let's Talk

Stay Informed

Get occasional updates about our company, research, and product launches.
Subscribe