Marcus Andrey Study
Ler em português Library

AI for UX

Frameworks

24 frameworks and techniques this course's lessons use, by area.

Each card opens the full framework: when to use it, the steps, an example, pitfalls and a template. The frameworks of every course are in one list, with a filter.

AI & design

AI adoption ladder
A four-rung scale for where a designer is with AI on one specific task, so you can coach the next step instead of pushing “AI adoption” in general. In Guiding designers through AI adoption
AI champions network
A small, rotating group of designers (one per 3–5 colleagues) who try tools, write playbook entries and run office hours, so the whole team learns from a few people's experiments. In Guiding designers through AI adoption, UX agents and skills: a guide for designers
AI usage guidelines
A one-page “how we use AI in UX” covering approved tools, data rules, review rules, transparency and where to ask, so designers can experiment safely without asking permission each time. In AI governance and data protection, Guiding designers through AI adoption
Context files
Files that AI agents read automatically (CLAUDE.md, AGENTS.md, DESIGN.md) that hold your principles, design-system rules and conventions, so every session starts from your standards instead of generic defaults. In AI for content design, AI-ready design systems, Build your first skill, Claude Design, Design specs for AI, Generating design with Claude Code, How a model learns: train one on your laptop, Prompt patterns for designers, UX agents and skills: a guide for designers, What AI is (and isn't)
Design tokens
Named design decisions (colour, spacing, type, radius) stored as data in one place, so design tools, code and AI agents all use the same values and you can check that they do. In Claude Design, Figma AI
Human-in-the-loop
AI proposes, a named human decides and stays accountable. Use it to set clear review, approval and undo points, both in your team's AI work and in the AI features you design. In AI design review process, AI governance and data protection, Agentic design
MCP
Model Context Protocol: an open standard for connecting AI agents to tools and data (design files, browsers, issue trackers), so you can decide which systems your team's agents may read or change. In AI tools landscape for designers, AI-ready design systems, Conversational and generative UI, Figma AI, Generating design with Claude Code, UX agents and skills: a guide for designers, What AI is (and isn't)
Spec-driven development
A way of working where every feature starts from written specs (requirements, then design, then tasks) that humans review and agents implement, so UX can own the experience before any code is generated. In Design specs for AI
Synthetic users
AI-simulated “users” or personas that answer research questions. Use them to brainstorm hypotheses and sharpen your research plan, never as a substitute for real users or as evidence. In AI in UX research, AI tools landscape for designers, Synthetic users and digital twins, What AI is (and isn't)
Trust calibration
Designing AI features so users trust them exactly as much as they deserve: not blindly (automation bias) and not never (wasted value), and testing that they do. In Agentic design, Designing for uncertainty, Ethics, bias and inclusion in AI design
Vibe coding vs production code
Fast AI-generated code is great for prototypes and risky as unreviewed production code. Use this to make the boundary explicit: where prototypes live, how they are labelled, and who decides what moves to production. In Prototyping with AI

DesignOps & capacity

Definition of Done for design
A short shared checklist (states, edge cases, accessibility, annotations, design-system usage) that says when design work is ready for handoff, agreed with developers and QA. In AI design review process
Weighted scoring
Criteria and weights agreed with stakeholders before any request is scored, which makes UX prioritisation transparent and less political. In Building an AI agent roadmap for your UX team

Enterprise UX

Contextual inquiry
Observe and interview users while they do their real work, in their real place, so you see the workarounds (Excel sheets, sticky notes) that interviews and demos never show. In Guiding designers through AI adoption

Facilitation techniques

Affinity mapping
Write findings on sticky notes, cluster them silently, then name the clusters as insights, so a group can make sense of research together. In AI-assisted synthesis, step by step

Influence & change

ADKAR
Individual change runs through Awareness, Desire, Knowledge, Ability and Reinforcement; use it to diagnose where someone is stuck and pick the right fix. In Guiding designers through AI adoption
Kotter 8 steps
John Kotter's eight steps for leading organisational change, from creating urgency to anchoring the change in culture, adapted to building a UX practice. In Guiding designers through AI adoption

People leadership

Career ladder
A grid of levels × dimensions (craft, collaboration, impact, leadership) that makes expectations explicit, so growth and promotion conversations are fair and specific. In Guiding designers through AI adoption
Design critique
A structured session where designers give feedback on work against goals and principles, kept separate from approval, so the work improves without anyone defending their taste. In AI design review process, Design specs for AI
Individual development plan
One page per designer with strengths, growth goals from the career ladder, actions, support and evidence of done, so growth becomes a plan you review together instead of a hope. In Guiding designers through AI adoption
One-on-one meetings
A recurring meeting that belongs to the report, not to you. It builds trust, surfaces problems early and drives growth, and a shared running doc keeps it focused. In Guiding designers through AI adoption
Psychological safety
A shared belief that the team is safe for interpersonal risk-taking. It lets you build a team where people raise problems, admit mistakes and question ideas early. In Guiding designers through AI adoption
Situational leadership
Adapt your style (direct, coach, support, delegate) to the person's competence and confidence on this specific task, instead of leading everyone the same way. In Guiding designers through AI adoption

Strategy & vision

Now-Next-Later roadmap
A roadmap organised by problems or themes and three time horizons instead of features and dates, so you can show direction and confidence without promising what you can't deliver. In Building an AI agent roadmap for your UX team
Saved only on this device.

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