Approach

UX leads. AI builds.
Users validate.

Every project I take on follows the same core principle: understand the people first, then decide what to build. Technology choices come last — after I have observed the actual workflow, identified the real pain points, and validated that a solution will genuinely help.

This approach has taught me that the most valuable AI systems are often invisible to their users. They remove friction, handle tedious steps, and let people focus on the judgments that require human expertise.

To apply this systematically, I have built a suite of research-driven tools that encode UX principles into my workflow — from color theory and eye-tracking research to human-centered design heuristics. These tools ensure that every design decision is grounded in established research, not just intuition.

1

Listen & Observe

I start by interviewing the people who do the work — process owners, operations staff, domain experts. I watch how they actually complete their tasks, noting workarounds and pain points that are invisible in process documentation. At Ergomotion, this revealed that customs brokers had developed manual shortcuts that no system had captured.

2

Prototype & Test

Rather than building a complete system, I ship a working prototype as fast as possible and put it in front of real users. Their reactions tell me more than any specification document. For the Pallet Calculator, I built the same capability two different ways — deterministic and AI-driven — to learn which approach users actually trusted.

3

Build with the Right Tool

AI is powerful, but it is not always the right answer. I choose the cheapest, most reliable tool for each step — deterministic logic for rules-heavy calculations, small language models for simple parsing, large models only when the task demands it. This keeps systems fast, debuggable, and affordable.

4

Close the Loop

I train the people who use the system to be its testers. Their ongoing feedback becomes the quality assurance layer. At Ergomotion, process owners became the QA team, and their feedback shaped the final automation pipeline. The system improves because the people closest to the work are continuously involved.

Research-Driven Toolkit

Custom Agents That Encode UX Principles

Rather than relying on ad-hoc design reviews, I have built specialized tools that apply established UX research systematically. Each agent encodes principles from academic research and industry best practices — ensuring consistent, evidence-based design decisions.

Color Theory Analyst

Nielsen Norman Group, IxDF, WCAG 2.1

Evaluates color harmony, the 60-30-10 rule, contrast ratios, color psychology, and brand alignment. Catches issues like accent overuse, poor contrast, and inconsistent color meaning before they reach users.

9 analysis modules · Weighted scoring · WCAG compliance

Eyetracking Principles Agent

Nielsen & Pernice "Eyetracking Web Usability"

Simulates where users look based on eye-tracking research — priority spots, F-pattern scanning, banner blindness, and visual weight. Identifies when important content is placed where users will not fixate.

Priority spot mapping · F-pattern analysis · Banner blindness detection

UI/UX Testing Protocol

Nielsen's 10 Heuristics, WCAG 2.1 AA

A 9-module RPA testing system that mimics human behavior — visual design, navigation, interactivity, responsive design, accessibility, performance, and content quality. Produces weighted scores with prioritized fixes.

9 modules · 100-point scoring · Severity-ranked findings

Design Intelligence Database

Curated from design systems, style guides, UX research

A searchable knowledge base with 67 visual styles, 96 color palettes, 57 font pairings, and 99 UX guidelines. Uses BM25 search to match project requirements to evidence-based design recommendations — no expensive AI calls needed.

67 styles · 96 palettes · 57 font pairings · 99 guidelines

How These Tools Fit Into My Workflow

Principles

Start with the user, not the technology

The best AI systems solve problems people actually have — not problems that are interesting to engineers.

Use the cheapest tool that works

Expensive models should be the last resort, not the first choice. Most work can be done with simpler, faster approaches.

Keep humans in the loop

Automation should augment human judgment, not replace it. Critical decisions need human oversight.

Ship and learn

A working prototype in front of real users teaches more than months of planning. Iterate based on what you observe.