Semantic search (RAG) in Blenheim.
AI search over your data - wired into a Blenheim workflow, not bolted on the side.
What semantic search (RAG) actually does
Search that understands intent, not just keywords. With the right workflow automated, nine hours of admin a week could drop to about one.*
*Illustrative example only, based on 9 hours a week of admin falling to about 1 hour a week. Actual results vary by workflow and business.
When harvest peaks in March, rosters, contractor invoices and compliance records all land at once. We automate that paperwork so vintage gets your full attention.
Less admin.
More weekend.
No theatre.
What you get
If we build the right slice first, Blenheim teams feel the difference inside the first month.
- 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 AI theatre
- No annual contracts
Not your typical AI agency.
*Every engagement is scoped and quoted up front. Results vary by workflow and business.
How much is the admin really costing you?
Nine hours a week of admin is 468 hours a year. That could drop to about 52.*
*Illustrative, based on 9 hours a week of admin at a typical 80% automation rate. The calculator uses your own numbers.
Business in Blenheim.
Marlborough is New Zealand's largest wine region, with almost 31,000 hectares of vines, around two thirds of the national total.
Marlborough put New Zealand on the international wine stage with its Sauvignon Blanc in the 1980s. Grape harvest runs to mid-April and peaks in March, with seasonal wine work from late January to May.
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.
Straight answers
Anyone else in this space using semantic search (RAG)?
Plenty. Average search time drops from 6 minutes to 12 seconds. The interesting question is rarely "does it work" - it's "is your team ready to use the output." That's what we'd scope on the call.
What if our Blenheim doesn't have any data ready?
Most don't. Getting the data into shape - ingestion, cleaning, the lightweight contracts you need before any model is useful - is part of the engagement. For semantic search (RAG) specifically, we typically run that work on Pinecone, Claude, Postgres pgvector, Vercel AI SDK and assume messy starting conditions from day one.
What's the smallest engagement you'd take on?
A two-week paid discovery for Blenheim businesses that aren't sure whether the build is worth doing at all. You get a one-page write-up of what we'd build, what we'd skip, and what it would cost. About 30% of those discoveries end with us recommending you don't proceed.
Does it keep up with KiwiSaver changes?
It has to. The minimum employer contribution rose to 3.5 per cent on 1 April 2026 and rises to 4 per cent on 1 April 2028.
Can the AI run on New Zealand-hosted cloud?
Yes, the options now exist. Microsoft opened a New Zealand cloud region in December 2024 and AWS followed in September 2025, both with local data residency.
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.