Semantic search (RAG) in Rotorua.
Semantic search (RAG) that lives in your stack, not on a vendor's roadmap. Shipped from Bay of Plenty.
Rotorua, up close.
Rotorua is known for agriculture, forestry and wood processing, geothermal and tourism, and it is one of New Zealand's most-visited cities.
In 2021 Te Uru Rākau New Zealand Forest Service located one of its two headquarters in Rotorua.
Rotorua runs on forestry, wood processing and one of the country's busiest visitor economies. We build AI that handles bookings, timber orders and the reporting behind both.
From one-person trades to national organisations, we find the hours :)
The questions a public sector buyer asks, answered up front: privacy impact, the NZISM, where the data lives and how an algorithm is held to account.
*Illustrative example based on nine hours a week of admin. Actual results vary by workflow and business.
How Kiwi Dynamics works
We find the one workflow costing Rotorua businesses the most hours, ship a working slice into production in weeks, prove it pays for itself, then harden it and hand it over.
Made for New Zealand paperwork.
Ask questions across your manuals, contracts and records and get answers with the source attached, not a guess.
- The Public Service AI Framework
- Xero, founded in New Zealand
- ACC levies set by industry
Less admin.
More weekend.
No theatre.
What you get
What changes for Rotorua teams after this lands: the work that used to need a person stays done, the work that needs a person gets done with their attention undivided.
- Indexes Drive, SharePoint, Notion, Slack, your CRM
- Returns answers with source links - no hallucinations
- Permissioned so staff only see what they should
- Re-indexes nightly so results stay fresh
- No annual contracts
- No AI theatre
Not your typical AI agency.
*Every engagement is scoped and quoted up front. Results vary by workflow and business.
Good questions, answered
What happens if we want to swap a vendor out later?
Semantic search (RAG) is built behind a small adapter layer specifically so swapping a model provider or a data source is a one-day job, not a re-architecture. Pinecone, Claude, Postgres pgvector, Vercel AI SDK are our defaults, but the build is intentionally portable.
Do you have proof this works for Rotorua businesses?
Direct case study: Average search time drops from 6 minutes to 12 seconds. Happy to walk you through full numbers on a call.
Is semantic search (RAG) worth it for a smaller Rotorua?
Often, yes - and counterintuitively the ROI is sometimes faster than for the big end of town because there's less integration overhead. We'll tell you honestly on the scoping call if it isn't.
How does this fit the Public Service AI Framework?
The framework, led by the Government Chief Digital Officer, asks for safe, transparent and accountable AI. Agencies that sign the Algorithm Charter also commit to transparency in how they use algorithms.
Can it keep track of ACC levies?
Yes. ACC work levies are set by the classification unit your work falls under, and self-employed people are invoiced after filing their tax return.
Let's chat
StartContact us
Tell us what you're trying to do and we'll reply with how we'd build it, no obligation.
Was this helpful?
Thanks, your comment is with our team.