# NN/g latest articles and announcements The latest articles and announcements from Nielsen Norman Group This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## AI Can Help Write an Article, but It Can't Stand Behind It DevFeed: [AI Can Help Write an Article, but It Can't Stand Behind It]() Original publisher: [Read original article]() Author: Raluca Budiu Published: 2026-09-11T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [Generative AI](), [User experience (UX)](), [Microsoft]() Tags: [ai](), [ai-authored](), [ai-content](), [ai-editing](), [ai-writing](), [article](), [copilot](), [genai](), [generative-ai](), [microsoft](), [ux](), [writing]() ### AI overview The article explains that NN/G uses AI during its editorial process for writing clarity, formatting, and critique, while humans retain editorial judgment and responsibility for published content. It describes a rigorous review cycle involving topic selection, multiple revisions, and checks for logical coherence, UX accuracy, and copy. AI tools such as Copilot in Microsoft Word and Grammarly help make writing more concise and clear, especially for authors who are not professional writers or speak English as a second language. ### Source excerpt NN/G uses AI for clarity, formatting, and critique, but humans retain editorial judgment and responsibility for every article. ## Test Complex Interactions Earlier with AI Prototyping DevFeed: [Test Complex Interactions Earlier with AI Prototyping]() Original publisher: [Read original article]() Author: Megan Chan Published: 2026-09-11T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [User interface design](), [cursor]() Tags: [ai](), [article](), [case-studies](), [conversational-ai](), [cursor](), [design](), [prototyping]() ### AI overview AI prototyping tools enable teams to create high-fidelity, interactive prototypes of complex interfaces and test them with users earlier in the design process. The article discusses how Ramp used Cursor to prototype an AI chat-based expense-policy editor and uncover usability issues and edge cases. ### Source excerpt AI tools make it feasible to build fully interactive prototypes of complex interfaces so you can test them with users earlier in the design process. ## Using AI for UX Work: Study Guide DevFeed: [Using AI for UX Work: Study Guide]() Original publisher: [Read original article]() Author: Tanner Kohler Published: 2026-09-04T17:00:00Z Content type: tutorial Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [User interface design]() Tags: [7-deadly-ai-sins-for-ux](), [ai](), [ai-adoption-in-ux-teams](), [ai-assistant-for-designers](), [ai-content-editor](), [ai-design-assistant](), [ai-for-ux](), [ai-governance-for-ux](), [ai-hallucinations-in-ux](), [ai-ideation-partner](), [ai-in-ux](), [ai-intern-analogy](), [ai-research-assistant](), [ai-ux-workflows](), [ai-virtues-for-ux](), [ari-ai-intern](), [article](), [care-prompt-framework](), [context-ask-rules-examples](), [designer-as-strategist](), [ethical-ai-in-ux](), [future-of-ux-roles](), [generative-ai-for-ux](), [guide](), [human-in-the-loop-ux](), [large-language-models-in-ux](), [nielsen-norman-group-ai](), [nn-g-study-guide](), [prompt-engineering-for-ux](), [prompt-templates-for-ux](), [reliable-ai-use](), [ux](), [ux-and-ai](), [ux-study-guide-ai]() ### AI overview A study guide on using AI selectively in UX workflows, emphasizing human judgment, user research, design context, writing voice, and evolving UX roles. ### Source excerpt Unsure where to start? Use this collection of links to our articles and videos to learn about the best ways to use artificial intelligence for UX work. ## UX Conference November Announced (Nov 16 - Nov 19) DevFeed: [UX Conference November Announced (Nov 16 - Nov 19)]() Original publisher: [Read original article]() Published: 2026-09-03T04:50:49Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [AI Strategy](), [Artificial Intelligence](), [Accessibility]() Tags: [ai](), [best-practices](), [design](), [event](), [training](), [ux](), [web]() ### AI overview Live online UX training courses covering best practices, hands-on exercises, AI-enhanced design workflows, AI product strategy, user research with AI, AI experiences, design systems, and user experience analytics. Sessions are offered for Asia/AU and the USA, with optional UX Certificate specialties. ### Source excerpt Take up to 2 in-depth training courses, teaching user experience best practices for successful design. Live online training focused on long-lasting skills for UX professionals. Nov 16 - Nov 19, 2026 (Americas) | Nov 17 - Nov 20 (Asia/AU). ## UX Conference September Announced (Sep 14 - Sep 25) DevFeed: [UX Conference September Announced (Sep 14 - Sep 25)]() Original publisher: [Read original article]() Published: 2026-09-01T20:37:45Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [User interface design](), [AI Strategy](), [AI Chat]() Tags: [ai](), [best-practices](), [collaboration](), [design](), [evaluation](), [event](), [management](), [skills](), [training](), [ux]() ### AI overview NN/G announces live virtual UX training courses running September 14-25, 2026. The program covers UX best practices, design systems, usability testing, AI-related UX strategy and writing, collaboration, and certification pathways. ### Source excerpt Take up to 5 in-depth training courses, teaching user experience best practices for successful design. Training focused on long-lasting skills for UX professionals. September 14 - September 25, 2026. ## The Custodial Era of UX: Cleaning Up After AI DevFeed: [The Custodial Era of UX: Cleaning Up After AI]() Original publisher: [Read original article]() Author: Anna Kaley, Raluca Budiu Published: 2026-08-28T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [User experience (UX)](), [Artificial Intelligence](), [Usability](), [Accessibility](), [Information Architecture](), [User interface design]() Tags: [accessibility](), [ai](), [article](), [cognitive-load](), [complexity](), [information-architecture](), [interaction-design](), [mental-models](), [speed](), [usability](), [ux]() ### AI overview AI enables teams to create content, prototypes, code, and working features faster than UX teams can evaluate them, creating UX debt. The article describes UX's role in reviewing AI-generated work, assessing its usefulness and usability, and restoring clarity, accessibility, trust, and coherence. ### Source excerpt AI lets teams build faster than UX can evaluate. UX can adapt by building shared judgment, accelerating evaluation, and guiding AI-generated designs. ## AI Can't Replace Real Research in Empathy Mapping DevFeed: [AI Can't Replace Real Research in Empathy Mapping]() Original publisher: [Read original article]() Author: Rachel Krause Published: 2026-08-28T17:00:00Z Content type: opinion Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [Usability](), [User interface design](), [data]() Tags: [ai](), [article](), [data](), [research](), [usability]() ### AI overview AI can help synthesize research already collected, but it cannot replace real user research in empathy mapping. AI-generated user statements may sound plausible yet lack evidence from specific people and contexts, while real observations and quotes provide the specificity that makes empathy maps useful. ### Source excerpt AI can help you organize research you've already collected, but it can't create research evidence about the specific, messy experience of real users. ## UX Conference November Announced (Nov 9 - Nov 13) DevFeed: [UX Conference November Announced (Nov 9 - Nov 13)]() Original publisher: [Read original article]() Published: 2026-08-24T06:48:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [User experience (UX)](), [Agile](), [Artificial Intelligence](), [Information Architecture]() Tags: [agile](), [ai](), [best-practices](), [collaboration](), [event](), [information-architecture](), [interaction-design](), [training](), [ux]() ### AI overview An NN/G announcement for November 9-13, 2026 offers up to five live online UX courses covering best practices, AI product strategy, design systems, interaction design, management, Agile, research, and information architecture. Participants can pursue optional UX Certificate specialty recognition. ### Source excerpt Take up to 5 in-depth training courses, teaching user experience best practices for successful design. Courses focused on long-lasting skills for UX professionals. November 9 - 13, 2026. ## Artificial Intelligence: Glossary DevFeed: [Artificial Intelligence: Glossary]() Original publisher: [Read original article]() Author: Caleb Sponheim Published: 2026-08-21T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [AI Agent](), [AI Development](), [Algorithms](), [Prompt Engineering]() Tags: [agentic-ai](), [agents](), [ai-agent](), [ai-definitions](), [ai-evals](), [ai-glossary](), [ai-glossary-for-ux](), [ai-hallucination](), [ai-terminology](), [ai-terminology-for-product-teams](), [ai-terms](), [ai-terms-for-designers](), [ai-vocabulary](), [article](), [artificial-intelligence](), [artificial-intelligence-glossary](), [context-window](), [genai-glossary](), [generative-ai](), [generative-ui](), [glossary](), [knowledge-cutoff](), [large-language-model](), [machine-learning](), [model-context-protocol](), [prompt-engineering](), [prompt-injection](), [rag](), [tokens](), [ux](), [vibe-coding]() ### AI overview A plain-language glossary of artificial-intelligence terminology used in products and UX work. It explains concepts including agents, agentic systems, AI development, algorithms, AI-generated content, and AI-related claims, while noting that terminology can vary among vendors and researchers. ### Source excerpt Plain-language definitions of the AI terms that come up in product and design work, from tokens and context windows to agents, evals, and prompt injection. ## AI-Generated Images Can Perform as Well as Stock Photography DevFeed: [AI-Generated Images Can Perform as Well as Stock Photography]() Original publisher: [Read original article]() Author: Rachel Banawa Published: 2026-08-21T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [.NET MAUI]() Tags: [ai](), [analysis](), [article](), [collaboration](), [images](), [photography](), [statistical-significance](), [teamwork]() ### AI overview AI-generated hero images did not produce a meaningful perception penalty compared with real stock photography in a study of 77 participants evaluating fictional consulting-firm webpages. Ratings were slightly higher for AI imagery, but only the small authenticity difference reached statistical significance. ### Source excerpt When users didn't know whether an image was AI-generated, the images we tested did not create any perception penalty compared to stock photos. ## One AI Output Is an Example, Not an Evaluation DevFeed: [One AI Output Is an Example, Not an Evaluation]() Original publisher: [Read original article]() Author: Raluca Budiu Published: 2026-08-14T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [Human-AI evaluation](), [LLM evaluation / benchmarking](), [benchmarking](), [User experience (UX)]() Tags: [ai](), [article](), [benchmarking](), [confidence-interval](), [eval](), [evaluation](), [language-models](), [llm](), [metrics](), [nondeterminism](), [performance](), [research](), [statistical-significance](), [usability]() ### AI overview One AI output is only an example, not a reliable evaluation. Because AI systems can produce different results from the same input, teams should assess them with multiple representative inputs, repeated runs, quantitative metrics, and confidence intervals. ### Source excerpt One output cannot establish how well an AI system performs. Evaluate with multiple representative inputs, repeated runs, and confidence intervals. ## Dogfooding vs. QA vs. User Research DevFeed: [Dogfooding vs. QA vs. User Research]() Original publisher: [Read original article]() Author: Therese Fessenden Published: 2026-08-07T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [dogfooding](), [FIRST]() Tags: [article](), [bugs](), [development](), [dogfooding](), [qa](), [qc](), [quality-assurance](), [quality-control](), [user-research](), [user-testing]() ### AI overview Dogfooding--using a company's own products internally--can reveal bugs, broken flows, crashes, and missing features while building empathy and shared ownership. The article explains that it complements but cannot replace user research, because insiders understand the product too well to represent real users. It also distinguishes genuine dogfooding from performative displays of loyalty. ### Source excerpt Dogfooding, or using your own products internally, helps catch bugs, but it can't replace user research: your team knows too much to represent real users. ## How to Decide When an AI Tool Is Worth Keeping DevFeed: [How to Decide When an AI Tool Is Worth Keeping]() Original publisher: [Read original article]() Author: Caleb Sponheim Published: 2026-08-07T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [Artificial Intelligence](), [Google]() Tags: [ai](), [ai-adoption-decisions](), [ai-productivity-claims](), [ai-tool-evaluation](), [ai-tool-tradeoffs](), [ai-trial-period](), [article](), [evaluating-ai-tools](), [evaluation](), [evidence-based-ai-adoption](), [google](), [how-to-decide-if-an-ai-tool-is-worth-keeping](), [prove-framework](), [provisional-decision-making-with-ai-tools](), [task-based-evaluation](), [testing-an-ai-tool-against-a-task](), [tool](), [tool-selection-criteria](), [when-to-stop-using-an-ai-tool]() ### AI overview The article introduces PROVE, a lightweight framework for evaluating whether an AI tool is worth keeping for a specific task. It emphasizes defining the task first, comparing the tool with the existing workflow, and assessing problem alignment, risk, output quality, velocity, and experience. The framework is illustrated through an evaluation of Google's Gemini Notebooks for drafting editorial digests. ### Source excerpt Pressure to adopt AI isn't evidence that a tool helps. The PROVE framework tests one tool against one task and produces a provisional decision you can defend. ## UX Conference October Announced (Oct 26 - Oct 29) DevFeed: [UX Conference October Announced (Oct 26 - Oct 29)]() Original publisher: [Read original article]() Published: 2026-08-04T08:43:32Z Content type: news Language: en Sources: [NN/g latest articles and announcements]() Topics: [User experience (UX)](), [Artificial Intelligence](), [Usability]() Tags: [ai](), [conference](), [event](), [learn](), [skills](), [training](), [usability](), [user-research](), [ux]() ### AI overview NN/G announces live virtual UX training courses running October 26-29, 2026. The program covers UX best practices, hands-on exercises, collaboration, certification, and optional specialties including AI for design workflows, AI product strategy, usability testing, and AI-assisted user research. ### Source excerpt Take up to 2 in-depth training courses, teaching user experience best practices for successful design. Training focused on long-lasting skills for UX professionals. October 26 - October 29, 2026. ## Why You Need Mentorship and How to Get It Right DevFeed: [Why You Need Mentorship and How to Get It Right]() Original publisher: [Read original article]() Author: Evan Sunwall Published: 2026-07-31T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [User experience (UX)](), [Software]() Tags: [article](), [career](), [design](), [growth](), [user-research](), [work]() ### AI overview This article explains why mentorship is valuable throughout a career, challenges common reasons people avoid it, and describes how sustained guidance can improve work quality, confidence, relationships, and professional growth. ### Source excerpt Mentorship is an essential growth tool that offers substantial personal and career benefits, but only if you engage in it properly. ## No New Name Has Replaced "UX" DevFeed: [No New Name Has Replaced "UX"]() Original publisher: [Read original article]() Author: Rachel Banawa Published: 2026-07-31T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [User Experience](), [Usability](), [Artificial Intelligence]() Tags: [ai](), [ai-tools](), [article](), [usability](), [user-experience]() ### AI overview A survey of 604 technology and design professionals found that "UX" remains the default name for the field, despite the growth of related terms such as usability, human-centered design, customer experience, design, and experience design. The article explains that these labels coexist with overlapping meanings as product managers, broader research participation, and AI tools expand who contributes to research and design work. ### Source excerpt A survey of 604 tech and design professionals found that "UX" remains the default name for our field, while alternative names remain fragmented. ## UX-Context Design: Using UX Knowledge to Inform AI-Generated Design DevFeed: [UX-Context Design: Using UX Knowledge to Inform AI-Generated Design]() Original publisher: [Read original article]() Author: Tony Alicea Published: 2026-07-24T17:00:00Z Content type: article Language: en Sources: [NN/g latest articles and announcements]() Topics: [User experience (UX)](), [Artificial Intelligence](), [AI Models](), [Prompt Engineering]() Tags: [ai](), [ai-models](), [article](), [building](), [design](), [research](), [ux]() ### AI overview As AI increasingly generates interface designs, UX research and design deliverables must become curated context that reflects users, domains, and organizational design standards. The article explains that this context guides AI output away from generic designs and toward experiences suited to specific users and organizations. ### Source excerpt As more interface work is AI-generated, the output of research and design shifts from documents written for humans to curated context that guides AI.