Marcus Andrey Study
Ler em português Library

AI for UX · 9 min read

AI for UX

A practical path through AI for designers in five steps: understand AI, work with it, keep quality and safety, research with it, and design it into products. Then a section for people who lead design teams, and a plain-language glossary.

Five steps, in order, each with practical patterns, checklists and the points where a designer stays in charge. Facts about tools, plans and laws are dated "as of"; check them again before you rely on them.

  1. Step 1 · Understand AI

    • What AI is (and isn't)The starting point for designers new to AI: what today's AI tools actually do, the handful of ideas that explain their behaviour (tokens, context, training cut-off, probability), why they make things up, and what that means for design work.
    • How a model learns: train one on your laptopA step-by-step explanation, for designers new to AI, of what a language model is, how it is trained in three stages, what fine-tuning and LoRA change, and how to read a real training run done on a laptop, with the mistakes it made.
    • AI tools landscape for designersA beginner's map of the AI tools designers meet in late 2026: the five kinds of tool, which one fits which design task, the data and security questions to ask, and a simple way to decide whether a tool is worth keeping.
    • Figma AIA beginner's guide to Figma's AI in late 2026: what the agent and the other AI features do, how seats and AI credits work, the data settings to check, and how to try it safely on real work.
    • Claude DesignA beginner's guide to Anthropic's Claude Design in late 2026: what it makes, how to set up your design system, what changed when it moved into every Claude conversation, how it compares with the Figma agent and Claude Code, and what to check first.
    • Your design career in the AI eraWhat the evidence actually says about AI and design jobs, kept apart from opinion: early-career hiring, which roles are growing and shrinking, how designers feel. Then the skills that hold their value, how to show AI use honestly in a portfolio, and a plan you can start this month.
  2. Step 2 · Work with AI

    • Prompt patterns for designersHow to brief an AI tool the way you'd brief a colleague: a five-part brief structure, ten reusable patterns for design work, the mistakes that produce generic output, and how to keep a prompt library your team can trust.
    • Design specs for AIWhy the written spec becomes the most important design artefact when AI can draw screens in seconds: the three layers of context, an AI-ready spec template with a worked example, the new context files (AGENTS.md, DESIGN.md), and how design fits into spec-driven development.
    • Prototyping with AIHow designers use prompt-to-prototype tools in late 2026: what each kind of tool is good at, how to brief one, how to use AI prototypes in usability tests without falling into the fidelity trap, and where a prototype ends and production code begins.
    • Generating design with Claude CodeA beginner's guide for designers to building prototypes with real components in Claude Code: the building blocks (CLAUDE.md, skills, MCP, plan mode), a ten-step Figma-to-code workflow, example instructions, who does what, and the guardrails that keep it safe.
    • AI for content designHow to use AI for UX writing without losing your product's voice: what it does well and badly, how to give it your voice and terminology, how to review AI copy, translation versus localisation, inclusive language, and when to tell users that text was written by AI.
    • AI for visual design: images and videoHow image and video generators work in plain words, the main tools designers use in late 2026, how to brief them for consistent results, what you may and may not do with the output (licences, copyright, the EU labelling rule, Content Credentials), and how to keep generated imagery accessible and fair.
    • AI-ready design systemsAI tools now read your design system to generate screens and code. What makes a system readable by machines as well as people: tokens in the DTCG format, components linked to code, files structured with intent, written usage rules, and connectors such as MCP. With a checklist to audit your own.
  3. Step 3 · Keep quality and safety

    • AI design review processHow to keep AI-generated design at your quality bar: six review gates scaled to the risk, a self-review checklist, the failure patterns to train your eye on, and why automated checks are never enough.
    • Ethics, bias and inclusion in AI designWhere bias in AI comes from, real cases that affect design work, why people over-trust AI and how to design against it, the manipulative patterns the law now bans, and practical habits that keep AI-assisted work fair and inclusive.
    • Accessibility with and for AITwo sides of the same job: using AI to make products more accessible without trusting it blindly, and making AI features themselves accessible. The current standards and laws, what the 2026 data shows, AI alt text and checkers, AI as assistive technology, and accessible chat interfaces.
    • Copyright and AI-generated assetsWhat designers need to know in late 2026 about owning and using AI-generated work: when output can be protected, what recent court cases decided, what the EU requires of model makers, which vendors offer legal protection, and how to keep a safe record of your own creative contribution.
    • AI governance and data protectionWhat any designer should know in late 2026 about using AI with real data and designing AI features: data protection basics, data classes and approved tools, the EU AI Act timeline as amended in 2026, workers' rights, and governance you can build into the design itself.
  4. Step 4 · Research with AI

    • AI in UX researchWhere AI genuinely helps across the research cycle and where people must stay in charge: planning, recruiting, moderating, transcribing, analysing and reporting, the five big risks, and a safe end-to-end workflow.
    • Synthetic users and digital twinsWhat AI-generated respondents are, what the research says about them (including a 2026 study with 604 people), where they help, where they mislead, and how to talk about them with stakeholders who want to skip real users.
    • AI-assisted synthesis, step by stepA practical method for using AI in research analysis without losing rigour: prepare and anonymise the data, read first, let AI do a first pass, challenge it, trace every insight to source, and report honestly. With what studies say about AI coding of interviews.
  5. Step 5 · Design AI into products

    • When not to use AIBefore designing an AI feature, decide whether it should use AI at all. Where AI fits and where it probably doesn't (Google PAIR), real cases where it backfired, the simpler alternatives that often win, the cost nobody sees, and a five-question check you can run with your team.
    • Agentic designHow to design AI features and agents people can trust: the spectrum of autonomy, principles for AI that acts on people's behalf, the UI patterns that make agents visible and controllable, and the notice each pattern depends on.
    • Conversational and generative UIHow to take AI beyond the chat box: why an agent must tell the screen what it's doing, how each of those notices becomes an interface state you design, how AG-UI (a 2026 open protocol) standardises them alongside MCP and A2A, and a no-code exercise to design the states yourself.
    • Designing for uncertaintyAI is sometimes wrong, and people need to know when. How to show confidence without fake precision, why explanations can backfire, how to word uncertainty, how to design errors and graceful failure, and how to help people trust AI exactly as much as it deserves.
    • Evals for designersEvals are the AI version of usability testing plus QA: structured tests of AI output against criteria. Why one good answer proves nothing, how designers write the test cases and rubrics, how automated judges work and fail, and a simple eval you can run without code.
    • Measuring AI featuresHow to know whether an AI feature actually helps: why people's sense of speed can be wrong, what the best studies found, which metrics to track (acceptance, correction, task success, errors introduced, retention), the limits of thumbs up and down, and a measurement plan you can adapt.
  6. Labs

    • Run a model on your laptopA hands-on lab: run an open language model on your own computer, with an app or a few terminal commands. What you need, which small models to try, what stays on your device, what we measured on a Mac, and how to judge the answers.
    • Generate images locallyA hands-on lab: generate images on your own computer with an open model. Three ways to start, how to read a model licence before you use the output, what we measured on a Mac, and what actually fixes hands and eyes (it isn't resolution).
    • Build your first skillA hands-on lab: turn a task you repeat into an AI skill, a small folder of instructions that Claude, ChatGPT, Copilot, Cursor and other tools can load. Write it, test it by hand, install it, check it on past work, and improve it.
    • Write an eval setA hands-on lab: build a small evaluation for an AI feature in a spreadsheet. Collect real cases, read the outputs, name the failures, count them, turn them into pass/fail criteria, and re-run after every change. Optional: automate it with promptfoo.
    • Write the voice of an AI assistantA hands-on lab: the system prompt is content design. Write an assistant's role, voice and tone, limits, how it says "I'm not sure" and when it hands over to a person; test it with tricky cases; and avoid the traps of flattery, fake friendliness and secrets in the prompt.
  7. For leads

    • Guiding designers through AI adoptionLeading AI adoption in a design team is change management, not a tool rollout. How to see where each person is stuck (ADKAR), how to talk about fear honestly, a six-week learning path, the structures that keep it going, how to protect craft and growth, and what not to do.
    • Choosing and piloting AI toolsHow a design team should choose an AI tool: start from the task, ask vendors the right questions about data, training, ownership and exit, run a short pilot that measures total time and quality, decide honestly, and roll out with training. Includes a worked example and a pilot plan you can copy.
    • UX agents and skills: a guide for designersWhat context files, skills, sub-agents, MCP connectors and plugins are, in plain words; when to use each; how to write a skill that works; five example skills for UX work; and how to review and share them safely.
    • Building an AI agent roadmap for your UX teamA method and template for deciding which AI agents your design team should build first: inventory the real work, find the parts that are gathering and checking, score candidates on value, risk, data sensitivity and effort, choose their form, and sequence them. With a worked example of a fictional team.
  8. Reference

    • Glossary52 AI terms a designer is likely to meet, in plain language, grouped by theme.
    • Frameworks24 frameworks and techniques this course's lessons use, by area.
    • Library242 books, articles, videos and courses cited in this course, grouped by the step they appear in.
Saved only on this device.

↑ ↓ to move · Enter to open · Esc to close