Case Study 003 · Independent Research
Design Process Innovation
AI‑Assisted UX Workflows
Human judgment first. AI acceleration second.
- Role
- UX Designer & Researcher
- Type
- Independent research
- Tools
- Claude, ChatGPT, Figma, Notion
- Status
- Ongoing practice · 2026
The Challenge
Design is a discipline that improves with friction: pushback, alternatives, a second opinion. Working solo means those feedback loops are either missing or slow. You can spiral inside your own assumptions without anyone to object.
AI doesn't replace a team. Used deliberately, it can recreate the structure of collaborative thinking.
It can propose alternatives you wouldn't have considered, surface objections before a stakeholder does, and compress research synthesis from days to hours. The challenge is keeping human judgment at the center, not outsourcing it.
3
Integrated phases: discovery, design, documentation
4
Tools in the stack, each with a bounded role
0
Decisions outsourced. AI accelerates; the designer decides.
Three-Phase AI Integration Model
How AI tools fit across discovery, design, and documentation, and where the line between AI and designer stays fixed.
- Discovery · Research synthesisAI compresses raw research data, surfaces patterns, and identifies contradictions across sources, without drawing conclusions. The interpretation is yours.
- Design · Ideation partnerAI generates alternatives to your proposed direction, stress-tests assumptions, and surfaces the strongest objection to your own idea. Momentum, without echo chambers.
- Documentation · Clearer deliverablesAI restructures design rationale into handoff-ready documentation. The thinking is yours; AI makes sure it's readable, complete, and structured for the next person.
Collaboration, recreated
AI recreates the structure of collaboration for solo designers.
Judgment is the filter
Human judgment remains the filter. AI accelerates; the designer decides.
Synthesis is the biggest gain
The largest efficiency gain comes from turning raw research into focused insight, faster.
In Practice
Three scenarios that show what this looks like as a working method, not as theory.
| Phase | Situation | How AI Is Used | Designer's Responsibility |
|---|---|---|---|
| Research synthesis | Five user interviews. Thirty pages of notes. | I feed the raw patterns to Claude and ask: “What tensions or contradictions exist across these responses?” It surfaces the friction, not conclusions. | Deciding what the friction means. |
| Ideation | A proposed flow direction. | I ask for three alternatives, then for the strongest objection to my original idea. | Defending the direction or abandoning it. The pushback, not the alternatives, is where the real thinking happens. |
| Documentation | Design rationale in plain language: why this decision, what was traded off, what would break it. | AI restructures it into a handoff-ready document, faster and cleaner. | The thinking happens before the prompt. It's still mine. |
The Tool Stack
Four tools, each with a defined role. The discipline is not mixing them, and keeping each bounded to what it's actually good at.
| Tool | Assigned Role | Used For | Boundary |
|---|---|---|---|
| Claude | Strategic thinking · Synthesis | Compressing interview notes, structuring problem frames, and stress-testing design rationale. Strongest at nuance and sustained argument. | Long-context reasoning, not where the design decision itself gets made. |
| ChatGPT | Variation · Rapid alternatives | Fast generation of alternatives, copy variations, and quick-turn lookups. | Quantity over depth. Judgment is applied afterward, to select and refine. |
| Figma | Design · Decision-making | Where the actual design decisions are made and tested. AI informs what goes in; Figma is where conclusions are drawn. | Not a place where AI makes choices. A place where the designer does. |
| Notion | Research capture · Synthesis docs | Prompt logging and synthesis documentation: what was asked, what was useful, what failed. | Captures and documents the process. Doesn't generate or decide. |
Over time, the Notion log builds an institutional memory of the AI-augmented process.
Where Human Judgment Stays
The line between what AI does and what the designer does isn't ambiguous. It's deliberate. Letting that line blur is where AI augmentation becomes AI dependence.
The Designer
- Defines the problem worth solving
- Interprets research with context and empathy
- Makes the design decisions
- Evaluates AI outputs against user needs
- Takes responsibility for the final work
- Knows when to ignore the AI entirely
The AI
- Compresses and finds patterns in raw data
- Generates alternatives quickly
- Surfaces objections and edge cases
- Restructures documentation for clarity
- Accelerates repetitive synthesis tasks
- Asks useful questions back
AI supports the process. The designer owns the decisions.
A More Deliberate Way to Work
The value of AI in design is not that it removes the need for judgment. It creates more opportunities to apply judgment, by reducing the time spent organizing information, generating initial alternatives, and restructuring documentation.