{ "name": "BASIC UX", "url": "https://basicux.com", "summary": "UX design principles for systems that people and AI agents use. Five principles, each asked of both users: Beauty, Accessibility, Simplicity, Intuitiveness, Consistency.", "author": "Dan Smith", "firstPublished": { "date": "2016-06-29", "venue": "UX Magazine", "url": "https://uxmag.com/articles/basic-ux-a-framework-for-usable-products" }, "version": "2.0", "updated": "2026-10-15", "license": "CC BY 4.0", "users": { "people": "See and use the screen.", "agents": "Read the accessibility tree, the HTML, robots.txt, llms.txt, structured data, APIs and WebMCP tools.", "delegation": "Questions for products where an agent acts on a person's behalf." }, "position": [ "One build serves both users. The accessible page is the agent-ready page.", "The people questions always come before the agent questions.", "No separate layer for agents: people and agents get the same content, prices and labels." ], "principles": [ { "id": "beauty", "name": "Beauty", "people": { "lead": "Is it aesthetically pleasing?", "questions": [ "Is it aesthetically pleasing?", "Does it follow the style guide?", "Are high-quality visuals used?", "Is it properly aligned?" ], "summary": "A good-looking design feels easier to use. Designers use style guides so small flaws do not make the product look broken." }, "agents": { "lead": "Is the page code clean?", "summary": "AI agents read page code and look at screen pictures. Clean code and a steady layout help agents find buttons without mistakes.", "questions": [ "Does the screen order match the code order?", "Does the layout stay still with nothing covering any button?", "Is the HTML page code valid with 1 h1 heading and a title?" ], "sources": [ { "title": "web.dev, Build agent-friendly websites (2026)", "url": "https://web.dev/articles/ai-agent-site-ux" } ] }, "delegation": { "question": "Can a person check the agent's plan and results fast?", "note": "Maggie Appleton wrote in 2026 that people need plans they can see.", "sources": [ { "title": "Maggie Appleton, Planning with Agents (2026)", "url": "https://maggieappleton.com/planning-agents" } ] } }, { "id": "accessibility", "name": "Accessibility", "people": { "lead": "Can everyone use it?", "questions": [ "Can everyone use it?", "Does it comply with standards?", "Is it cross-platform compatible?", "Can people with ADHD, dyslexia or other learning differences read the text?" ], "summary": "Accessibility means all people can use the product. Designers must build for people with poor sight, hand limits or other disabilities." }, "agents": { "lead": "Can an agent read and use it?", "summary": "In a 2026 AudioEye study, AI agents finished 96% of tasks on an accessible page. They finished 31% on a page that was not.", "questions": [ "Does every button have a role and name in the accessibility tree?", "Is the text in the HTML code before JavaScript runs?", "Can an agent do public tasks without CAPTCHA or robots.txt blocks?" ], "sources": [ { "title": "Nielsen Norman Group, AI Agents as Users (2026)", "url": "https://www.nngroup.com/articles/ai-agents-as-users/" }, { "title": "AudioEye, AI agent task completion on inaccessible websites (2026)", "url": "https://www.prnewswire.com/news-releases/audioeye-study-finds-up-to-68-drop-in-ai-agent-task-completion-on-inaccessible-websites-302888585.html" } ] }, "delegation": { "question": "Can the person stop the agent or take over anytime?", "note": "Luke Wroblewski wrote in 2025 that people must start and stop agents.", "sources": [ { "title": "Microsoft, Guidelines for Human-AI Interaction (2019)", "url": "https://www.microsoft.com/en-us/haxtoolkit/library/" }, { "title": "Luke Wroblewski, Agent Management Interface Patterns (2025)", "url": "https://www.lukew.com/ff/entry.asp?2106=" } ] } }, { "id": "simplicity", "name": "Simplicity", "people": { "lead": "Does it make life easier?", "questions": [ "Does it reduce the user's workload?", "Is it free of clutter and repetitive text?", "Is its functionality necessary?", "Is the text short and plain, with 1 idea per sentence?" ], "summary": "More choices make people slower to decide. Show only what people need for their task, and use short, plain words." }, "agents": { "lead": "Does it take the fewest steps?", "summary": "Elnaffar and Rashidi cut agent steps by 30% in a 2026 store test. You can cut steps with an API, which is a direct software link.", "questions": [ "Is there a short path like llms.txt, JSON-LD, an API or WebMCP?", "Does each form or tool do 1 job?", "How much text must the agent read to finish the task?" ], "sources": [ { "title": "Elnaffar and Rashidi, Designing Agent-Ready Websites for AI Web Agents (2026)", "url": "https://arxiv.org/abs/2607.12056" }, { "title": "The /llms.txt file", "url": "https://llmstxt.org/" }, { "title": "WebMCP draft specification", "url": "https://webmachinelearning.github.io/webmcp/" } ] }, "delegation": { "question": "Is checking the agent's work easier than doing the work yourself?", "note": "Anthropic found in 2026 that skilled users watch agents instead of approving steps.", "sources": [ { "title": "Anthropic, Measuring AI agent autonomy in practice (2026)", "url": "https://www.anthropic.com/research/measuring-agent-autonomy" } ] } }, { "id": "intuitiveness", "name": "Intuitiveness", "people": { "lead": "Is it easy to learn?", "questions": [ "Is the functionality clear?", "Can the user reach their goal with little or no instruction?", "Can the task be repeated without further instruction?", "Can the user predict the outcome?", "Can a reader with the least schooling understand it the first time?" ], "summary": "A product should be easy to learn so people do not have to learn it again. Use common button shapes and link colors." }, "agents": { "lead": "Does it say what it does?", "summary": "AI agents need every action named in plain text. In a 2026 MERJ test, a bad label made an agent click Cancel 25 times.", "questions": [ "Does every button, link or tool name its exact action?", "Does text stay on the page to say what happened?", "Are actions that cannot be undone clearly marked?" ], "sources": [ { "title": "MERJ, How AI Agents Use Websites, Where They Fail, and What to Fix (2026)", "url": "https://merj.com/blog/agent-interaction-research" } ] }, "delegation": { "question": "Does the person see the plan first, with a way to undo?", "note": "Victor Yocco wrote in 2026 that users need to see plans and undo actions.", "sources": [ { "title": "Victor Yocco, Designing for Agentic AI, Smashing Magazine (2026)", "url": "https://www.smashingmagazine.com/2026/02/designing-agentic-ai-practical-ux-patterns/" } ] } }, { "id": "consistency", "name": "Consistency", "people": { "lead": "Does it match the system?", "questions": [ "Does it reuse existing patterns and designs?", "Is its language, imagery, and branding consistent with the system?", "Does it appear in the right place at the right time?", "Does it perform consistently every time?" ], "summary": "Keep colors, spacing, fonts and forms the same across the product. Reuse the same parts so people know what to expect." }, "agents": { "lead": "Does it act the same every time?", "summary": "Jakob Nielsen wrote in July 2026 that people and AI agents need the same view. Giving both the same prices stops mistakes.", "questions": [ "Do people and agents get the same text, prices and labels?", "Does the same name always go to the same web address?", "Does the API or tool do the same thing as the screen?" ], "sources": [ { "title": "Jakob Nielsen, UX Roundup: Web Design for AI Agents (2026)", "url": "https://www.uxtigers.com/post/ux-roundup-20260731" } ] }, "delegation": { "question": "Does it say it is AI and ask before spending, deleting or sharing data?", "note": "OpenAI says a person should check paid or permanent agent actions.", "sources": [ { "title": "OpenAI, A practical guide to building agents (2025)", "url": "https://cdn.openai.com/business-guides-and-resources/a-practical-guide-to-building-agents.pdf" } ] } } ], "positionSources": [ { "title": "Jim Nielsen, Thoughts on AX (2025)", "url": "https://blog.jim-nielsen.com/2025/thoughts-on-ax/" }, { "title": "Adrian Roselli, OpenAI, ARIA, and SEO: Making the Web Worse (2025)", "url": "http://adrianroselli.com/2025/10/openai-aria-and-seo-making-the-web-worse.html" }, { "title": "TechPolicy.Press, The Web Is Being Made Accessible for AI, Not People (2026)", "url": "https://www.techpolicy.press/the-web-is-being-made-accessible-for-ai-not-people/" } ], "skills": { "page": "https://basicux.com/skills.html", "bundle": "https://basicux.com/files/basic-ux-skills.zip", "design": { "name": "basic-ux-design", "download": "https://basicux.com/files/basic-ux-design.zip", "does": "Build rules for both users: how a coding agent should design and build a page people and AI agents can both use." }, "audit": { "name": "basic-ux-audit", "download": "https://basicux.com/files/basic-ux-audit.zip", "does": "Scores a page for people and for agents with Playwright, lists every failed check, and writes agent-view.yaml.", "run": "node scripts/assess.mjs [--brand brand.json]" }, "install": "Unzip into your agent's skills folder (for Claude Code, ~/.claude/skills/). Each skill folder holds a SKILL.md." }, "readerStandard": "Text is written for a reader with ADHD, dyslexia or another learning difference, and for the least schooling a reader might have: reading grade 6 or below, about 15 words a sentence and none over 25, paragraphs of 1 to 3 sentences, headings of 8 words or fewer, literal words, every term explained once." }