Back to Portfolio Case Study · Independent Research

AI-Assisted UX Workflows

Human judgment first. AI acceleration second.

AI-Assisted UX Workflows

Role: UX Designer & Researcher Type: Independent Research Tools: Claude, ChatGPT, Figma, Notion
3
Integrated Phases
Discovery · Design · Documentation
4
Tools in Stack
Each with a defined, bounded role
0
Decisions Outsourced
AI accelerates. The designer decides.
Part 01

The Challenge

Step 01 · EmpathizeThe 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. But used deliberately, it can recreate the structure of collaborative thinking: proposing alternatives you wouldn't have considered, surfacing objections before a stakeholder does, and compressing research synthesis from days to hours. The challenge is keeping the human judgment at the center — not outsourcing it.

Part 02

The Process

Step 02 · DefineResearch Framework
Three-Phase AI Integration Model
How AI tools were integrated across discovery, design, and documentation — and where the line between AI and designer stays fixed
01
Discovery
Research Synthesis
AI compresses raw research data, surfaces patterns, and identifies contradictions across sources — without making conclusions. The interpretation is yours.
02
Design
Ideation Partner
AI generates alternatives to your proposed direction, stress-tests assumptions, and surfaces the strongest objection to your own idea. Momentum, without echo chambers.
03
Documentation
Clearer Deliverables
AI restructures design rationale into handoff-ready documentation. The thinking is yours; AI makes sure it's readable, complete, and structured for the next person.
Key Insight
AI doesn't replace collaboration — it recreates the structure of it for solo designers.
Key Insight
Human judgment remains the filter. AI accelerates; the designer decides.
Key Insight
The biggest gain is in synthesis — turning raw research into focused insight, faster.

Step 03 · IdeateIn Practice

Three scenarios that show what this actually looks like — not as theory, but as a working method.

Phase 01 · Research Synthesis

Five user interviews. Thirty pages of notes. I feed the raw patterns to Claude and ask for synthesis — not conclusions. The prompt is: "What tensions or contradictions exist across these responses?" The AI surfaces the friction. I decide what it means.

Phase 02 · Ideation

I pitch a flow direction and ask for three alternatives, then ask for the strongest objection to my original idea. The pushback — not the alternatives — is where the real thinking happens. Having to defend a direction, or abandon it, sharpens both options.

Phase 03 · Documentation

I write the design rationale in plain language — why this decision, what was traded off, what would break this. AI restructures it for a handoff doc. Faster, cleaner, still mine. The thinking happened before the prompt.

Step 04 · PrototypeThe Tool Stack

Four tools, each with a defined role. The discipline is not mixing them — keeping each bounded to what it's actually good at.

Claude
Strategic Thinking · Synthesis

Long-context reasoning and research synthesis. Used for compressing interview notes, structuring problem frames, and stress-testing design rationale. Strongest at nuance and sustained argument.

ChatGPT
Variation · Rapid Alternatives

Fast generation of alternatives, copy variations, and quick-turn lookups. Used when the goal is quantity over depth — get five versions of something quickly, then apply judgment to select and refine.

Figma
Design · Decision-Making

Where the actual design decisions are made and tested. AI informs what goes into Figma; Figma is where the conclusions are drawn. Not a place where AI makes choices — a place where the designer does.

Notion
Research Capture · Synthesis Docs

Research capture, prompt logging, and synthesis documentation. Tracking what was asked, what was useful, what failed — building an institutional memory of the AI-augmented process over time.

Part 03

The Solution

Step 05 · TestWhere 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 patterns raw data
Generates alternatives quickly
Surfaces objections and edge cases
Restructures documentation for clarity
Accelerates repetitive synthesis tasks
Asks useful questions back