AI tools are more than just stylish designs or advanced technology. They help create moments that truly make life easier and more enjoyable. Yet user experience (UX) designers are faced with a challenge: How do you blend AI into daily products without feeling like AI is taking over?
This challenge is our call to action. UX designers want to use AI in a way that feels natural and ethical. After all, AI should serve as a supportive buddy rather than a bossy robot.
The goal of a UX designer is to improve human experiences by creating AI systems that understand and fulfill their users’ needs, and amaze them. To do so most effectively, UX designers need to rethink how to engage with AI systems to improve user experience in design.
Designing for AI
At first glance, designing for AI seems straightforward. You could plug in a ChatGPT API and allow it to work for you. Content creation becomes a breeze, data aggregation a no-brainer, and suddenly, we're living in a design utopia, right? Well, as I ventured deeper into integrating with AI, I discovered it's more than just making tasks easier. It's about reimagining the way UX designers approach software design using some familiar techniques.
Unleashing the Power of AI Personas
In one of the first courses I took on Designing for AI, I heard about considering AI as another person to design for. It has its own needs and constraints that must be considered during the design process. Enter the benefit of AI Personas as the potential solution for addressing these multifaceted challenges.
Three main types of AI personas exist: creative AI, optimizer AI, and aggregator AI. To better articulate this concept, let’s take an example of designing a new slide presentation app.
The first step in the design process is to understand the domain and the pain points. Let’s say research points to the following insights:
- Individuals in an organization spend 20%-40% of their time each week tweaking visuals in slide presentations.
- Deck creation requires hours of research and coordination to create an effective presentation.
- Many presentations require weekly updates as data changes.
- A typical presentation deck receives 20 to 30 comments inline, via email, and chat, which delays content updates.
And let’s say there’s a new AI tool that can help with some of these tasks. UX designers can leverage AI to address these concerns.
- Creative AI helps the user quickly create visually appealing and content-rich presentations.
- Optimizer AI helps users create better presentations that fit their needs by learning over time what works best for each user.
- Aggregator AI summarizes data sources, comments, related emails, and chat content for easier consumption and real-time updates.
Each of these AI personas have specific needs that when met can maximize the output.
Creative AI
Creative AI, as you might guess, excels at imaginative tasks — it generates compelling graphics and text, or offers design templates. However, it needs clear direction on brand guidelines and the audience in order to execute effectively. Consider questions like:
- Should the presentation be sparse and minimal, like Apple’s design system, or more colorful and playful, like Lego’s?
- Is this content best presented to an audience or is it a reference document? If you create the text for an audience, keep it sparse and populate the speaker notes. If it’s a reference document, you can structure it more like a report with a more text-heavy layout.
- Is this content accessible to all users, including those who may struggle with different colors, text sizes, or alternative text descriptions?
Optimizer AI
Optimizer AI is an expert in efficiency. It helps make mundane tasks easier, like automatically setting up slide transitions and formatting bulleted lists. However, it needs to understand the context of the presentation and have a history of past presentations to index.
It also needs to understand feedback on each presentation, such as whether one presentation was better received than another. This data guides the AI in making contextually relevant suggestions to polish the presentation and other presentations in the future.
Aggregator AI
Aggregator AI primarily focuses on pulling together disparate data and information. Imagine making a presentation using many relevant and current data sources, such as emails, articles, and other presentations. Aggregator AI helps integrate all data points smoothly and clearly. There’s no need to constantly update that monthly metrics presentation!
In addition to outside data sources, this AI persona needs access to all user comments in the presentation. Ideally, the AI persona should also have any relevant emails or chats. This makes updates easier for the user by offering a summary of both user preference and user behavior. It also can leverage its friend, Creative AI, to recommend changes.
The 6 Principles of Designing with AI
A critical component to the success of leveraging AI, regardless of persona and its unique needs, is integration. Effective integration ensures data streams are ready to improve output and reduce user input. To maximize output, here are six fundamental principles every engineer should implement when designing with AI, and how they could apply to the hypothetical slide presentation app
Transparency and Explainability
The principle of transparency and explainability in AI design means making the AI's decision-making clear to users. It involves creating interfaces and experiences that show what the AI is doing and why it is doing it. This principle is important to build trust. It helps users feel comfortable and confident with how AI affects their experience with a product.
In the presentation app, the designer could add an AI feature to help users design their presentations. This feature would offer suggestions for design layouts and color schemes.
This AI feature will also explain why it recommends certain options. For example, if the AI suggests a certain layout, it can explain how this layout improves audience engagement, which relies on information about the type of content and user behavior.
You could achieve this using a simple tooltip or a side panel to gather insight into how the AI makes recommendations. This approach not only accelerates the creation of presentations but also educates users on solid design principles.
Adaptability and Personalization
AI systems excel in learning from interactions and adjusting their behavior to better serve individual user needs over time. This dynamic learning capability allows for the personalization of user experiences in unprecedented ways. Designing for adaptability means creating interfaces that can evolve, offering personalized experiences based on user behavior, preferences, and feedback.
In the presentation app example, if a user frequently picks simple designs and a certain color scheme, the AI will remember this. It can then show these options in future suggestions. It could also adjust the complexity and frequency of tips and tutorials based on the user's skill level. This would help new users learn better and make things easier for experienced users.
Ethical Considerations and Bias
Incorporating AI into design demands a rigorous examination of ethical considerations and the proactive mitigation of bias. This principle focuses on ensuring fairness, accountability, and inclusiveness in AI-driven solutions. UX designers need to consider the different users they have. They should ensure that AI systems learn from diverse datasets, which also helps to avoid repeating current biases.
Several companies, such as Google and IBM, have established AI principles to follow. The AI in our presentation app example can learn from a collection of presentations. These presentations come from different industries, cultures, and design styles, which enables the creation of design recommendations that are inclusive and cater to a diverse range of user preferences. Additionally, users could have the option to give feedback if they think a recommendation is biased or unsuitable. This helps the AI learn and improve its suggestions.
Consistency and Reliability
Consistency and reliability are foundational to user adoption and satisfaction with AI-enabled products. This principle emphasizes the importance of repeatability and accuracy in AI responses and actions.
Design strategies should include clear communication about the AI’s capabilities and limitations to avoid overpromising or creating unrealistic expectations. You can improve reliability by ensuring AI systems are strong and tested in many different situations. This helps reduce errors and misunderstandings.
The presentation app, for example, could include clear documentation and settings for the AI features. You could present the AI's suggestions as options instead of commands. This way, users can decide whether to follow them. Ensuring the AI's recommendations are consistently high quality and relevant will also build trust over time.
Error Handling and Support
Despite advances in AI, errors and misinterpretations are inevitable. Effective error handling and support mechanisms are essential in maintaining user trust and engagement. This involves designing systems that recognize when they are failing and offer useful, accessible support options to the user.
For example, our presentation app can notice when users have trouble with tasks. It can then offer helpful suggestions, or let them connect with a support agent. As mentioned with ethical considerations and bias, providing feedback will help the AI learn and improve, making it invaluable.Sustainability
As AI models become more complex, their energy consumption and environmental impact grow. Designing for sustainability involves optimizing AI algorithms and their implementation for energy efficiency, minimizing the carbon footprint of digital products. This principle extends to user interactions to encourage behaviors that reduce energy consumption (e.g., streamlining queries or interactions to minimize computational load). It also involves transparency about the environmental impact of using AI-enabled services with the goal of empowering users to make informed choices about their digital consumption.
The presentation app's energy efficiency can be improved by simplifying the AI's decision-making. This will lower the computational load for common tasks.Moreover, the information about the energy efficiency of different design choices could inform users, encouraging them to adopt more sustainable practices. For example, suggesting design features that work well on low-power devices can help. Also, giving tips on effective presentation delivery can support this goal.
The Value of Incorporating AI in Design
By thoughtfully incorporating AI into product design, you can unlock many benefits, including increased efficiency, better user experiences, and a positive impact on business results.
AI can help you balance quality, innovation, and budget. It can also assist in adjusting designs for specific environments. AI can make a significant impact in these areas, but give yourself some grace; there’s a learning curve involved when you start using AI-based design tools.
Let’s Explore an AI Partnership
By embracing transparency, adaptability, and a commitment to ethical principles, UX designers have the opportunity to forge a future where technology and humanity intersect in harmony. Together, we can navigate the complexities of this new frontier, crafting experiences that resonate deeply with the very essence of human interaction.
Let’s connect to explore how we can help you take advantage of this new AI era.
