Design for Generative AI: Beyond Conversational Interaction

In the last post I covered some conventional UX practices and methodologies that apply to generative AI interfaces but are not exclusive to generative AI. What are some methodologies or principles that are more specific to generative AI that differ from the UX design for other, more traditional applications? First, we define generative AI interfaces are those that use artificial intelligence to create or modify content, such as text, images, audio, or video. They are different from other applications in that they require a high level of user trust, control, and feedback. Some of the UX design principles, approaches, or methodology that are specific or important for generative AI interfaces are:

Transparency: The user should be able to understand how the generative AI works, what are its capabilities and limitations, and how it uses the user's data. This can be achieved by using clear labels, icons, tooltips, explanations, and examples to communicate the AI's functionality and purpose ¹ ².

Control: The user should be able to influence the generative AI's output, such as by providing input, setting parameters, choosing options, or editing the result. This can be achieved by using sliders, buttons, menus, checkboxes, or text fields to allow the user to adjust the AI's behavior and outcome ¹ ².

Feedback: The user should be able to see the generative AI's output, evaluate its quality and relevance, and provide feedback to the AI. This can be achieved by using progress bars, previews, ratings, comments, or suggestions to show the user the AI's progress and result, and to collect the user's opinion and preference ¹ ².

Iteration: The user should be able to refine the generative AI's output, such as by repeating, modifying, or combining the results. This can be achieved by using undo, redo, save, delete, or merge functions to enable the user to experiment and improve the AI's output ¹ ².

Some examples of generative AI interfaces that use these principles are:

Framer: A design tool that uses generative AI to create realistic mockups and prototypes based on the user's sketches. It uses a magic wand icon to indicate the AI feature, a slider to control the level of detail, a preview to show the AI's output, and a save function to store the result ¹.

Photoshop: A photo editing tool that uses generative AI to enhance or transform images. It uses labels and tooltips to explain the AI features, such as neural filters, content-aware fill, or sky replacement. It also uses buttons and menus to allow the user to select and adjust the AI options, a progress bar to show the AI's progress, and an edit function to modify the result ¹.

Notion: A note-taking and collaboration tool that uses generative AI to generate text based on the user's input. It uses a sparkles icon to indicate the AI feature, a text field to provide the input, a preview to show the AI's output, and a rating function to collect the user's feedback ¹.

Diagram: A diagramming tool that uses generative AI to create diagrams based on the user's text. It uses a label and an example to explain the AI feature, a text field to provide the input, a preview to show the AI's output, and a merge function to combine the results ¹.

(1) Emerging UI/UX Patterns in Generative AI: A Visual Guide. https://www.whitespectre.com/ideas/emerging-ui-ux-patterns-in-generative-ai/.

(2) Design Principles for Generative AI Applications - arXiv.org. https://arxiv.org/abs/2401.14484.

(3) Redefining UX Design for Generative AI Models in Enterprise. https://law.stanford.edu/2023/11/16/redefining-ux-design-for-generative-ai-models-in-enterprise/.

Why You Need a Designer with a Good Eye (and Not Just a Good AI)

As a hiring manager in the tech field, you probably have a lot of resumes to sift through. You might be tempted to look for candidates who have impressive credentials, such as degrees from prestigious universities, certifications from online courses, or portfolios full of AI-generated designs. But before you make a decision, let me ask you a question: do you really want a designer who relies on artificial intelligence or bootcamps to do their work, or do you want a designer who has a good eye for visual design and a natural instinct for creating engaging user experiences?

Don't get me wrong, I'm not saying that AI or bootcamps are bad. In fact, they can be very useful tools for designers to learn new skills, explore new ideas, and speed up their workflow. But they are not enough to make a great designer. A great designer needs more than just technical knowledge or software proficiency. A great designer needs a sense of aesthetics, a flair for creativity, and a passion for solving problems. These are qualities that can't be taught by a machine or a curriculum. They can only be developed by innate talent, experience, and a nurturing education.

Let me give you some examples of why you need a designer with a good eye (and not just a good AI).

- AI design tools are useful, but not complete. AI design tools, such as Adobe Sensei, Wix ADI, or Canva, can help designers generate layouts, logos, or graphics based on some inputs or preferences. They can save time and effort, and sometimes produce surprising results. But they can also be limited, generic, or inconsistent. They can't capture the nuances, emotions, or contexts of the design problem. They can't understand the user's needs, goals, or expectations. They can't create a seamless user experience that is intuitive, engaging, and delightful. That's why you need a designer who can use AI as a tool, not a crutch. A designer who can evaluate, refine, and customize the AI-generated designs to suit the specific project and audience. A designer who can add their own touch of personality, originality, and elegance to the design.

- Bootcamps are good for learning how to use specific applications, but can't teach instinct or visual design. Bootcamps, such as General Assembly, Springboard, or Designlab, can teach designers how to use popular design applications, such as Sketch, Figma, or Adobe XD. They can also teach them the basics of design principles, such as color, typography, or hierarchy. They can provide them with feedback, mentorship, and networking opportunities. But they can't teach them how to have a good eye for visual design. They can't teach them how to develop a natural instinct for creating engaging user experiences. They can't teach them how to be creative, innovative, or empathetic. These are skills that can only be honed by practice, experimentation, and observation. That's why you need a designer who has a good eye for visual design. A designer who can create beautiful, functional, and user-friendly designs that stand out from the crowd. A designer who can balance form and function, art and science, logic and emotion.

So, the next time you are looking for a designer, don't just look at their credentials, look at their portfolio. Look for designs that show a good eye for visual design and a natural instinct for creating engaging user experiences. Look for designs that are not only technically sound, but also aesthetically pleasing, emotionally appealing, and contextually relevant. Look for a designer who can use AI or bootcamps as a means to an end, not an end in itself. Look for a designer who can make your products and services not only usable, but also desirable.

Trust me, you won't regret it.