Five UX principlesPublished in 2016
Two user typesPeople and agents
Free open licenseCC BY 4.0

BASIC UX for people and AI agents

These 5 principles from 2016 check a page for people and AI agents.

Scroll to explore

The framework

Five principles check pages for people and agents

Dan Smith wrote BASIC UX for UX Magazine on June 29, 2016. It gives 5 principles to check user experience, or UX, which is how a person uses a product.

Jakob Nielsen wrote in July 2026 that a page has 2 user types. People look at the screen. AI agents read the HTML page code and the accessibility tree, which lists each button and name.

PrinciplePeopleAgents
Beauty Is it aesthetically pleasing? Is the page code clean?
Accessibility Can everyone use it? Can an agent read and use it?
Simplicity Does it make life easier? Does it take the fewest steps?
Intuitiveness Is it easy to learn? Does it say what it does?
Consistency Does it match the system? Does it act the same every time?
5Principles
21Questions for people
15Questions for agents
2016First published

Principles

The 5 principles

Beauty

PeopleIs it aesthetically pleasing?

AgentsIs the page code clean?

A good-looking design feels easier to use. Designers use style guides so small flaws do not make the product look broken.

Questions for people

  • Is it aesthetically pleasing?
  • Does it follow the style guide?
  • Are high-quality visuals used?
  • Is it properly aligned?

Questions for agents

AI agents read page code and look at screen pictures. Clean code and a steady layout help agents find buttons without mistakes.

  • 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?

Accessibility

PeopleCan everyone use it?

AgentsCan an agent read and use it?

Accessibility means all people can use the product. Designers must build for people with poor sight, hand limits or other disabilities.

Questions for people

  • 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?

Questions for agents

In a 2026 AudioEye study, AI agents finished 96% of tasks on an accessible page. They finished 31% on a page that was not.

  • 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?

Simplicity

PeopleDoes it make life easier?

AgentsDoes it take the fewest steps?

More choices make people slower to decide. Show only what people need for their task, and use short, plain words.

Questions for people

  • 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?

Questions for agents

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.

  • 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?

Intuitiveness

PeopleIs it easy to learn?

AgentsDoes it say what it does?

A product should be easy to learn so people do not have to learn it again. Use common button shapes and link colors.

Questions for people

  • 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?

Questions for agents

AI agents need every action named in plain text. In a 2026 MERJ test, a bad label made an agent click Cancel 25 times.

  • 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?

Consistency

PeopleDoes it match the system?

AgentsDoes it act the same every time?

Keep colors, spacing, fonts and forms the same across the product. Reuse the same parts so people know what to expect.

Questions for people

  • 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?

Questions for agents

Jakob Nielsen wrote in July 2026 that people and AI agents need the same view. Giving both the same prices stops mistakes.

  • 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?

Agents at work

When an agent acts for a person

Jakob Nielsen wrote in July 2026 that checking an agent's work takes time. These 5 questions check how a person watches an AI agent.

  1. Beauty: Can a person check the agent's plan and results fast?

    Maggie Appleton wrote in 2026 that people need plans they can see.

  2. Accessibility: Can the person stop the agent or take over anytime?

    Luke Wroblewski wrote in 2025 that people must start and stop agents.

  3. Simplicity: Is checking the agent's work easier than doing the work yourself?

    Anthropic found in 2026 that skilled users watch agents instead of approving steps.

  4. Intuitiveness: Does the person see the plan first, with a way to undo?

    Victor Yocco wrote in 2026 that users need to see plans and undo actions.

  5. Consistency: Does it say it is AI and ask before spending, deleting or sharing data?

    OpenAI says a person should check paid or permanent agent actions.

Position

One build serves both users

Jim Nielsen wrote in 2025 that people come before AI agents. A good page has no separate version that hides text or changes prices.

Adrian Roselli said in 2025 that AI-only code can leave out disabled people. One accessible page gives people and AI agents the same view.

Sources

The research behind the lenses.

Skills

Free Agent Skills for Figma and coding

Get basic-ux-design, basic-ux-audit and basic-ux-figma for Figma, Claude Code, Codex, Cursor or GitHub Copilot.

See the three skills Download all three (.zip)

Put it to work

Five principles for everyone

Get the BASIC UX skills Principles as JSON View on GitHub

BASIC UX is free under the CC BY 4.0 license and is in UX framework lists by Maze, Ramotion and Gapsy Studio.