Methodology
24 years of building has shaped a way of working that sets me apart before any tool enters the picture. AI accelerates the work; experience is what makes it trustworthy.
How I work
Every engagement follows the same core discipline: understand the problem before proposing a solution, design with the people who will use the thing, build what you design, and verify it works in context. Discovery, design, build, iterate. End to end. Each cycle feeds back into the next: lessons from build sharpen the next discovery.
I work across the full stack of a problem. On the design side: stakeholder facilitation, user research, information architecture, wireframes, high-fidelity UI, design systems in Figma with token pipelines. On the build side: production React and Vue, component libraries, Storybook, accessibility to WCAG 2.2, and the front-end engineering that turns a design into a working product. The combination means fewer handoff gaps: the person designing the interaction is the person writing the code.
What makes the methodology distinctive is the range it draws on. 24 years across signage fabrication, museum fitout, wayfinding, brand systems, enterprise portals, government accessibility programmes, and digital twins. That breadth creates pattern recognition that specialists in a single domain do not develop. A wayfinding project and a component library are the same problem at different scales: tokens, variants, consistency, constraints.
The toolkit
The core stack is Figma for design, React and Vue for front-end development, and Storybook for component documentation. Design tokens flow from Figma variables through a pipeline into CSS custom properties, keeping design and code in sync.
Beyond the core: SketchUp Pro for 3D modelling, SolidWorks (historically) for technical drawing, .NET and C# on the back end, PostgreSQL and SQL Server for data, Azure and Microsoft 365 across the platform layer. The specific tools shift by engagement; the discipline of choosing the right tool for the task does not.
AI as accelerator
AI did not replace the methodology. It made the existing methodology faster. The differentiator is not "I use AI" (everyone uses AI) but demonstrated orchestration and human-in-the-loop judgement: naming the tool, explaining the selection rationale, documenting where the model got it wrong, and showing how experience caught it before it shipped. Many teams describe this as AI-first development. The difference is whether the person choosing the tools has enough experience without AI to know what good looks like.
I reach for different tools depending on the task:
Claude / Claude Code
Architecture reasoning, code generation, document analysis, content strategy. Claude Code for multi-file refactoring and codebase-aware edits. Where the reasoning quality justifies the cost and latency.
GitHub Copilot
Inline code completion, boilerplate generation, test scaffolding. Faster than Claude for line-by-line development within an established codebase. I use it where speed matters more than reasoning depth.
Figma AI
Layout generation, auto-layout suggestions, asset search. Useful for rapid prototyping within an established design system. Not a replacement for design thinking, but an accelerator within it, and for preparing workshop boards.
Copilot 365 & Copilot Studio
Tenant-resident data gathering via a retrieval-augmented generation (RAG) pattern, document analysis and presentation scaffolding within Microsoft 365. Used where the task requires access to organisational content the other tools cannot reach, or where process automation earns its place. Copilot Studio for building custom AI agents and automation workflows within the Microsoft ecosystem.
Where AI gets it wrong
AI tools produce confident, plausible output that is regularly wrong in ways that require domain experience to catch. Examples from my work:
Hallucinated metrics
AI will confidently generate performance metrics, cost savings percentages, and user satisfaction scores when asked to write case studies. Without verifiable source data, these numbers are fabricated. Experience catches it because you know which metrics you actually measured.
Overclaimed seniority
Given a career history, AI consistently inflates titles, scope, and ownership. "Contributed to" becomes "led." "Supported" becomes "directed." "Second of two leads" becomes "co-equal technical lead." A 24-year career with real progression catches this because the actual arc is more interesting than the inflated version.
Accessibility false positives
Automated accessibility tools (including AI-assisted ones) pass components that fail in practice. A contrast ratio passes the algorithm but fails for the actual user group. Keyboard navigation "works" but the focus order makes no sense. Manual testing against real WCAG 2.2 criteria catches what automation misses. It is, after all, built for humans.
Code that compiles but misses context
AI-generated code frequently produces syntactically correct solutions that violate project conventions, ignore existing patterns, or introduce subtle regressions. Copilot will generate a component that works in isolation but breaks the design system's token pipeline. Good project structure, documentation and stage gates prevent compounding errors. The human in the loop catches what passes the linter.
The pattern across all four examples is the same: AI produces confident output that passes a surface check. Experience is knowing which surface checks to run, and when not to reach for AI at all.
The proof is in the portfolio
This site itself demonstrates the methodology. It was built with Claude Code, GitHub Copilot, and Figma AI. Every generated output was reviewed against the grounding document, verified against source facts, and corrected where the model got it wrong. The design tokens were extracted from Figma via an MCP pipeline, not generated by AI. The case study content was written from primary source material, not summarised by a model.
Client delivery. The AI workflow project is the clearest example: translating a university client's design system into a reusable AI skill, choosing Claude Code for the agentic build, Copilot 365 for tenant data, and Claude for the runtime. The practice manager asked me to present the method to my peers. The Anglo American ML platform demonstrates designing interfaces between human expertise and machine capability, working alongside an Azure ML pipeline in a 70+ developer programme. Beyond project work, the same orchestration stance shapes daily workflow: choosing the right AI tool for each task across documentation, code review and communications.
Personal R&D. The SRHS proof of concept applies the same orchestration stance outside client work: designing a three-layer IoT architecture that assigns different AI tools to different tasks based on their strengths, with a basic Home Assistant integration in development.