Designing AI Products and Features: Study Guide

Nielsen Norman Group published a study guide arguing that companies should not treat AI as a value proposition in itself, citing former CEO Jakob Nielsen's 2021 warning against overinvesting in technology without a clear understanding of how it solves real user needs. The guide collects 12 resources, including articles on scoping generative AI features, the four AI superpowers of content creation, summarization, basic data analysis, and perspective taking, and lessons from Perplexity head of design Henry Modisett. It recommends that product teams start with the problem rather than the technology and avoid adopting chat interfaces unless they meet real user needs.

Creating new AI-based features or integrating AI into existing products goes beyond simply adding an AI chatbot to your website. However, adding ✨AI✨ does not magically create value. In fact, in some cases, it’s a huge investment for a relatively small return. This collection of resources describes measured approaches to deciding whether AI adds value in the first place and gives specific recommendations for designing AI features based on our research. It’s easy to optimistically talk about AI as something that can swoop in and make anything easier. It’s also easy and somewhat more gratifying to skeptically talk about AI as completely overhyped and hollow. Neither approach is unilaterally true. We must give AI a real chance but be willing to call out whenever “ the emperor has no clothes on ” because it is not making a valuable difference. The Strategy and Value Proposition of AI Excited companies chasing after a new technology are not new. In 2021, well before the release of LLMs like ChatGPT, our former CEO, Jakob Nielsen, warned against https://www.nngroup.com/videos/relationship-ai-ux/ overinvesting in the promise of the tech https://www.nngroup.com/videos/relationship-ai-ux/ without a clear understanding of how it solves real user needs. There is nothing wrong with seeing AI as a powerful hammer in your toolbox, but there’s something seriously wrong with trying to find a nail to hit with your favorite hammer rather than thinking about what you’re trying to build. | Number | Link | Format | Description | | 1 | “Powered By AI” Is Not a Value Proposition https://www.nngroup.com/articles/powered-by-ai-is-not-a-value-proposition/ | article | Companies should lead with the value that AI implementations offer rather than counting on AI to create value. | | 2 | AI Features Must Solve Real User Problems https://www.nngroup.com/articles/ai-user-value/ | article | AI implementations created for novelty rarely produce real value. Seek to solve real pain points. | | 3 | AI Chat Is Not Always the Answer https://www.nngroup.com/articles/ai-chat-not-the-answer/ | article | Product teams must avoid rushing to adopt chat interfaces unless they meet real user needs. | | 4 | Scope in Generative AI Features https://www.nngroup.com/articles/scope-ai-features/ | article | Narrowly scoped AI features are easier to understand and have better user adoption. | | 5 | Four AI Superpowers: Where AI Improves Products https://www.nngroup.com/articles/ai-superpowers/ | article | AI’s four “superpowers” are content creation, summarization, basic data analysis, and perspective taking. | | 6 | Common-Sense AI Integration: Lessons from the Cofounder of Condens https://www.nngroup.com/articles/ai-integration-condens/ | article | Ask these 3 key questions to ensure AI integrations are valuable and appropriate. | | 7 | The UX of AI: Lessons from Perplexity https://www.nngroup.com/articles/perplexity-henry-modisett/ | article | Henry Modisett, head of design at Perplexity, shared advice for designing AI features. | | 8 | Generative UI and Outcome-Oriented Design https://www.nngroup.com/articles/generative-ui/ | article | Generative UIs could create custom interfaces for each user, focused on their desired outcomes. | | 9 | GenUI: AI-Generated Interfaces https://www.nngroup.com/videos/genui-ai-generated-interfaces/ | video | | | 10 | AI Agents as Users https://www.nngroup.com/articles/ai-agents-as-users/ | article | AI agents now interact with digital interfaces alongside humans, which requires rethinking what “user” means and prioritizing accessibility. | | 11 | What Is Your Site’s AI Chatbot for? Users Can’t Tell https://www.nngroup.com/articles/site-ai-chatbot/ | article | Users see little reason to use site-specific AI chatbots unless those chatbots solve problems that existing site features cannot. | | 12 | Don’t Start with AI, Start with the Problem https://www.nngroup.com/videos/dont-start-with-ai/ | video | Products deliver more value when teams start from the user problem rather than from the AI technology. | Prompt Assistance The power of LLM-based AI features is largely mediated by users’ ability to write good prompts. While newer models often yield useful outputs with underspecified prompts, they still cannot read people’s minds. To make matters worse, users don’t always know what they are looking for or what the AI is fully capable of. Thus, it’s critical to support users in their prompting efforts. | Number | Link | Format | Description | | 1 | Overcoming the Articulation Barrier in Generative AI Using Hybrid Interfaces https://www.nngroup.com/articles/ai-articulation-barrier/ | article | UIs that combine prompt-based inputs with a graphical user interface GUI can improve the usability of image-generation tools. | | 2 | Designing Use-Case Prompt Suggestions https://www.nngroup.com/articles/designing-use-case-prompt-suggestions/ | article | Well-designed use-case prompt suggestions support learnability and creativity, helping users explore what AI tools can do while setting realistic expectations. | | 3 | Prompt Suggestions https://www.nngroup.com/articles/prompt-suggestions/ | article | Prompt suggestions must be contextually relevant, personalized, and specific both to the task and to the user’s level of experience. | | 4 | Prompt Controls in GenAI Chatbots: 4 Main Uses and Best Practices https://www.nngroup.com/articles/prompt-controls-genai/ | article | Prompt controls can increase AI feature discoverability, educate and inspire, set constraints, and facilitate follow-ups. | | 5 | The Most Exciting Development in GenUI: Buttons and Checkboxes https://www.nngroup.com/articles/genui-buttons-and-checkboxes/ | article | AI chats generate simple UI elements to gather context, which reduces typing and memory load and produces more personalized results. | Product and Feature-Specific Recommendations Once you decide that AI can add value to a product or feature, you’d better build it correctly. These resources highlight specific recommendations and observations we’ve made about designing AI-powered products and features well. | Number | Link | Format | Description | | 1 | AI Summaries of Reviews https://www.nngroup.com/articles/ai-reviews/ | article | AI summaries of product reviews are well-received when they are specific and transparent. | | 2 | Product-Specific GenAI Needs to Write for the Web https://www.nngroup.com/articles/genai-write-for-the-web/ | article | Generative-AI outputs often violate web-writing principles. They should still be concise, scannable, follow the inverted pyramid, and use plain language. | | 3 | AI Discoverability: Amazon’s Mistakes https://www.nngroup.com/articles/discoverability-ai-amazon/ | article | Amazon’s ”Rufus” demonstrates that even valuable AI features have low impact if they aren’t noticed. | | 4 | AI Intranet Features: Current and Future https://www.nngroup.com/articles/ai-intranet-features/ | article | AI integrated into intranets can boost productivity, support career growth, and tailor experiences. | | 5 | AI on Intranets: 5 Valuable Features https://www.nngroup.com/videos/ai-intranets-features/ | video | | | 6 | The Proliferation and Problem of the ✨ Sparkles ✨ Icon https://www.nngroup.com/articles/ai-sparkles-icon-problem/ | article | The sparkles icon is inherently ambiguous, but it is becoming increasingly associated with AI. | | 7 | The 5 Qualities of Site-Specific AI Chatbots https://www.nngroup.com/articles/dimensions-of-ai-chatbots/ | article | Five qualities make site-specific AI chatbots trustworthy: handoff willingness, flexibility, proactivity, emotional responsiveness, and transparency. | | 8 | Crafting AI Explanations for Every Role in Your Enterprise https://www.nngroup.com/articles/crafting-ai-explanations/ | article | Different roles within an enterprise need different types of explanations for the same AI output. | | 9 | Context Architecture https://www.nngroup.com/articles/context-architecture/ | article | Applying information-architecture principles to AI systems helps agents interpret information and produce better-aligned responses. | | 10 | Designing AI Agents: 4 Lessons from China’s Qwen Agent https://www.nngroup.com/articles/designing-ai-agents/ | article | A study of Qwen’s AI agent yields four design lessons: support discoverability, reuse familiar patterns, handle personal data carefully, and protect user autonomy. | | 11 | 10 Guidelines for Designing Your Site’s AI Chatbots https://www.nngroup.com/articles/ai-chatbots-design-guidelines/ | article | Helpful site-specific AI chatbots state their capabilities clearly, offer relevant prompt suggestions, and quickly signal what they can see. | | 12 | Less Chat, More Answer: Site AI Chatbots Need to Get to the Point https://www.nngroup.com/articles/less-chat-more-answer/ | article | Users turn to site-specific chatbots for quick answers rather than conversation, so responses should be direct, scannable, and expandable. | | 13 | Explainable AI in Chat Interfaces https://www.nngroup.com/articles/explainable-ai/ | article | Explanation text in AI chat interfaces is intended to help users understand outputs, but current practices fall short of that goal. | | 14 | 4 Things GenAI Needs for Better Content Design https://www.nngroup.com/videos/genai-content-design/ | video | Product-specific genAI must follow common digital-writing practices to fit the way users scan. | State of AI-Product Design The resources in this section report on recommendations or cautions given at a specific point in time. While some highlight findings that still hold today, others have likely changed as AI’s capabilities have grown and its adoption in the UX field has evolved. | Number | Link | Format | Description | | 1 | Initial Impressions of ChatGPT’s Agent: Successful, Shaky, and Slow https://www.nngroup.com/articles/impressions-chatgpt-agent/ | article | ChatGPT’s agent could successfully book a restaurant reservation, but the process was slow and error-prone. 2025 | | 2 | The Relationship Between Artificial Intelligence and User Experience https://www.nngroup.com/videos/relationship-ai-ux/ | video | Focusing on user needs is more important than chasing a new technology. AI can potentially understand user intentions and make UX practitioners more productive. 2021 | | 3 | Is aggressive marketing influencing the UX of AI Agents? https://www.nngroup.com/videos/aggressive-marketing-ux-ai-agents/ | video | Over-hyped marketing of intelligent assistants might ultimately hurt people’s willingness to use them if the UX is disappointing. 2019 | | 4 | AI's Impact on New Technologies https://www.nngroup.com/videos/ais-impact-new-technologies/ | video | Jakob Nielsen observed that AI will be limited until it can understand both human language and intention. 2016 | | 5 | Handmade Designs: The New Trust Signal https://www.nngroup.com/articles/handmade-designs/ | article | As AI-generated content proliferates, users treat visibly human-made design as a signal of trustworthiness. | Podcast Episodes | Number | Link | Format | Description | | 1 | 36. AI & UX: Innovations, Challenges, and Impact ft. Henry Modisett https://www.youtube.com/watch?v=a1HZU2qEo1c&list=PLJOFJ3Ok idv78lCtzYaKUiO07CC rU0A&index=21&ab channel=NNgroup | podcast | Henry Modisett, head of design at Perplexity, shared advice for designing AI features. | | 2 | 43. Responsible AI feat. Paige Lord, Sr. Product Marketing Manager at GitHub https://www.youtube.com/watch?v=r0YbkFCyeAI | podcast | Paige Lord offers some insight into ways UX professionals can help create ethical AI products and services. | | 3 | 47. Designing AI Experiences: What to Consider feat. Caleb Sponheim PhD, NN/g https://www.youtube.com/watch?v=fn O6WjLgcs&list=PLJOFJ3Ok idv78lCtzYaKUiO07CC rU0A&index=8&ab channel=NNgroup | podcast | Designers tasked with creating AI-powered experiences must prioritize value and safety. | | 4 | 57. The Next Decade of UX: Why Psychology Matters More Than Ever feat. Thomas Watkins https://youtu.be/gLqGgw8Zlaw?si=HXCUuV0Tqfn8 sce | podcast | Designers must specify user intent so that the AI can create products that meet user needs. |