Findability for a large portfolio of government websites: where site search is heading, what to ask of a search platform, what a good AI answer shows, and how content shows up in AI assistants.
I'm Practice Lead, Findability, in MBIE's Search, AI and Findability team. The work itself is internal, so this page covers the general direction and how I go about it, not the plans.
Where site search is heading
Most government websites grew their own search, and most still match keywords and return a long list of pages. People don't search like that any more. They type whole questions, in everyday words, and expect an answer.
- Keyword search A long list of pages that contain the words you typed. Misspell one and you get nothing.
- Smarter search Synonyms, spelling, English and te reo Māori, and the most-asked questions tuned by hand.
- Answers A short answer drawn from the site's own pages, with its sources, and the full results underneath.
Each step only works if the content underneath is right. That's why findability is as much about the pages as the search box.
Questions I'd ask any search vendor
AI search demos well. These questions get past the demo:
- Answer one of our real questions, from our pages. Not your sample content, ours, typos and all.
- What happens when the answer isn't on our site? A good system says so. A risky one fills the gap.
- Show me where every sentence came from. Each claim should trace back to a page someone can check.
- Does it handle te reo Māori? Macrons, mixed-language questions, and pages in both languages.
- Where is our data stored and processed? And is any of it used to train someone else's model?
- How do we test answers before each release? A fixed set of questions with known answers, run every time.
What a good AI answer shows
AI-assisted search reads the question, finds the passages that answer it in the site's own pages, and summarises them with links back. On a government site, the answer has to earn trust. It should show:
- Where each part came from, with numbered links to the source pages
- When those pages were last updated
- The ordinary results underneath, for people who'd rather read the page
- A way to say it didn't help, and someone who reads that feedback
Showing up in AI assistants
People also get government guidance from Google's AI Overviews, ChatGPT, Copilot and Gemini, often without visiting the website. Generative engine optimisation (GEO) starts with checking what those assistants say, then fixing the pages they draw on. My AI Overviews accuracy report shows how that check works and why answers go wrong.
What I did
- Put together a findability roadmap, with search as one part of it
- Researched how search works across the websites, and wrote options and recommendations for where it goes next
- Wrote requirements for modern search, including AI-assisted search
- Was part of a vendor-neutral evaluation of AI and enterprise search platforms
- Worked on the approach to GEO, including how accurately AI Overviews represent government guidance
- Ran a cross-team workshop to shape the roadmap, and briefed leadership and the teams who run the websites
- Findability roadmap
- AI-assisted search
- Platform evaluation
- Requirements
- GEO