Semantic search (RAG) in Dunedin.
For Dunedin operators who want a working pilot in weeks, not a year-long programme.
What this is
AI search over your data
Search that understands intent, not just keywords. Your team types what they mean – and gets the right document, ticket, or product from across every system, with citations.
Average search time drops from 6 minutes to 12 seconds.
How it helps your Dunedin team
What you actually get.
- 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
The version of semantic search (RAG) that works for a Dunedin business is rarely the version a national vendor would sell you. We build the one that fits how your team actually operates – usually with fewer parts than the off-the-shelf pitch.
Average search time drops from 6 minutes to 12 seconds. For Dunedin teams, that almost always shows up as fewer interruptions and a calmer week, not a dashboard chart.
The Dunedin context, plainly.
Education, health, tech, and a tourism shoulder season that hits hard. AI helps Dunedin teams smooth the peaks and protect the people.
We work with teams in
What we build
Semantic search (RAG), tailored to Dunedin businesses.
- 01 Indexes Drive, SharePoint, Notion, Slack, your CRM
- 02 Returns answers with source links – no hallucinations
- 03 Permissioned so staff only see what they should
- 04 Re-indexes nightly so results stay fresh
Common questions
Before you book the call.
When does semantic search (RAG) actually pay back? +
Inside the first quarter, in our experience. We pick the first slice specifically because it's the highest-leverage workflow for a Dunedin – so the savings start landing before the rest of the build is finished.
How do you price semantic search (RAG) engagements? +
Fixed-scope pilots first, then either project pricing or a small monthly retainer for the ongoing work. No long lock-ins, no 18-month black-box deals. Most Dunedin businesses are surprised how small the first cheque is.
Can you walk us through a comparable build? +
Yes – on the first call we'll pick the closest engagement we've shipped to what you're describing and walk through the outcome, the headcount and the time it took. Average search time drops from 6 minutes to 12 seconds.
Will this run on our own infrastructure? +
Yes, where it makes sense. Semantic search (RAG) can sit entirely in your cloud account, with model calls routed through endpoints you control. We default to Pinecone, Claude, Postgres pgvector, Vercel AI SDK but the architecture supports your existing platform choices.
The honest version of a sales call.
No deck. No discovery doc. Just whether this is worth building and what it would cost.
Back to the form ↑