Issue 102

Agents among UX'ers

Hello, dear readers! 👋

In this issue, among other things:

• What is interface density and how to take it into account when designing

• What should be an effective design process in a company

• A guide to using native keyboards when designing mobile applications

• Comparison of the preferences of designers and users in the design of interfaces

• Agent-based UX — a really big milestone in the development of LLM

• How predictable is your PIN code

• …and much more!

Enjoy reading!

🗞 News and articles

The agentic era of UX. The future of digital experience is...

Earlier, I mentioned about the trend of AI agents and collected several successful examples. Alex Klein also wrote about agent-based UX and why the emergence and rapid development of AI agents is a really big milestone in the development of LLM and the experience of using them.

Alex's main idea is that in the previous paradigm, AI functions helped solve individual small tasks, but did not change the processes entirely - largely because of the companies themselves' view of how AI should be implemented in work.

For example, today ChatGPT will help you come up with ideas for a party, but will not send out invitations or order everything you need for the guests. With the advent of AI agents, users will be able to perform more complex tasks, sometimes completely autonomously. In such a paradigm, AI turns into a real partner who has weight in completing tasks, and most importantly, takes on a real operational and creative burden.

UI Density

Matthew Strom wrote about what interface density is, how it can manifest itself and how to take it into account when designing. In the article, he rethinks the conclusions of Edward Tufty from the book "The visual representation of large amounts of information."

Main thoughts:

• Density can be visual, informational, and temporal

• First of all, the density is assessed visually. The more information there is in the interface, the denser it is

• The density of information indicates how much data is placed in the interface. If the elements take up a lot of space but contain little data, then perhaps they should be excluded

• The density of information has a limit, and its perception depends on the audience. For example, an experienced trader can easily cope with a complex quotation table, but a second grader cannot

• Information density can be related to visual density. Usually, the higher the density of information, the denser its visualization will look

• When designing, it is necessary to take into account the principles of gestalt, which describe how people structure and perceive visual information

• The time density is determined by how quickly the interface responds and loads

• It is important to find a compromise between visual, information and time density, as well as take into account the context of working with the interface

Are you designing with the right keyboard in mind?

Ksenia Toloknova has released a very valuable guide on using native keyboards when designing mobile applications on iOS and Android. Her recommendations are based on market analysis, official documentation, and a conversation with developers.

In the article, Ksenia talked about what affects the appearance and behavior of keyboards, how they can be natively customized, and what types of built-in keyboards exist in iOS and Android.

She also showed many examples of using different types of keyboards depending on the scenario. For example, when entering an email, an SMS code, a password, and in other cases.

Comparison of Users and Designers Differences in Mobile Shopping App Interface Preferences and Designs

A group of Chinese researchers found out that ordinary users prefer warmer colors and many functions in the design of interfaces. Designers, on the contrary, choose cool shades and minimalistic design.

In 2018, researchers conducted an experiment aimed at comparing the preferences of designers and ordinary users. To do this, they selected the 40 most popular shopping apps in the Chinese App Store and asked participants to rate them on a scale from 1 to 9. A total of 35 users and 35 designers took part.