The areas I work in, and where I've done that work.
Three things I focus on: getting AI features into websites and services so they work and people can trust them, making sure people find the right information whether they use a website's search, Google or an AI assistant, and giving content the structure both depend on.
AI features people can trust
AI search, answer summaries and assistants: deciding what the feature should do, writing it down so it can be built and bought, testing the answers it gives, and fitting it into the content and the interface around it.
- Wrote requirements for modern, AI-assisted search across MBIE's websites
- Led a vendor-neutral evaluation of AI and enterprise search platforms
- Started out as a front-end developer, so I can follow how an AI feature is built, not only what it should do
- Build small AI applications of my own, which keeps me close to what models do with real content and what they cost to run, including the Ask about Miro assistant on this site
Found by people and by AI
Site and enterprise search: roadmaps, platform choice, requirements, and measuring whether people find what they came for.
People now ask ChatGPT, Copilot, Gemini and Google's AI Overviews before they visit a government website. Generative engine optimisation (GEO) is about making sure those answers are accurate and point back to the source.
- Developed a search roadmap and long-term recommendations for AI-assisted search at MBIE
- Worked on the search procurement: options paper and functional requirements
- Developed MBIE's approach to GEO, including assessing AI-visibility and audit tools
- Assessed how accurately Google AI Overviews represent government guidance
Structure AI can read
AI search and assistants answer from your content. Structure, taxonomy and metadata decide how good those answers can be.
- Information architecture, taxonomy, metadata and SEO for info.health.nz
- Information architecture and journeys for MSD's Analytics to the Front Line
Also
AI adoption in the public sector
Getting AI from a pilot into everyday use, within New Zealand's expectations on accessibility, privacy, te ao Māori and public trust, including the Public Service AI Framework.
- Briefed MBIE leadership and channel teams on AI-assisted search
- Facilitated a cross-team findability workshop that produced a roadmap and action plan
- Connected a network of government search and findability practitioners
Product and UX leadership
Product ownership, design systems, accessibility and working with vendors on national services.
- UX design lead for Book My Vaccine
- Co-led and product-managed Health New Zealand's enterprise Figma design system
- Coordinated WCAG 2.2 audits across public and staff platforms
How I like to work
- Vendor-neutral when comparing tools and platforms
- Decisions backed by test questions and evidence, not demos
- Plain English that leadership teams can act on
- Methods and documentation that stay with the team