Most of our Devonport engagements start the same way: a 20-minute call where the owner describes a workflow we've heard before in shape but never in detail. Semantic search (RAG) is then designed against the detail, not the shape.
For Devonport operators who want a working pilot in weeks, not a year-long programme.
What semantic search (RAG) actually does
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.
- 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
Built on: Pinecone Claude Postgres pgvector Vercel AI SDK
Without Koala Dynamics
With Koala Dynamics
What's different about doing this work in Devonport.
- Devonport is the freight gateway to Tasmania, where the Spirit of Tasmania sets the clock for a lot of local business.
- Ferry freight, agriculture, vegetable processing and logistics on the north west coast. Timetable-driven dispatch and customer updates are constant and still largely manual.
We work with teams across Devonport: Devonport CBD · East Devonport · Latrobe · Spreyton · Ulverstone.
Talk to us about this →
How we build semantic search (RAG) for a Devonport team.
We scope narrow, ship a working pilot, then harden it into production. The first slice is the highest-leverage workflow for your Devonport business, so value lands before the build is finished. AI search over your data.
Talk to usThe outcome for Devonport teams
The shape of the result for Devonport teams: Average search time drops from 6 minutes to 12 seconds. Built on Pinecone, hardened with the rest of the stack as it scales.
Not your typical AI agency.
Honest about what AI can and cannot do
Ships the one workflow that pays for itself
Hours given back, never the size of the invoice
*Every engagement is scoped and quoted up front. Results vary by workflow and business.
FAQ
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 Devonport - so the savings start landing before the rest of the build is finished.
Do you do hourly billing or fixed price?
Fixed price for the pilot, every time. After that it's your call - fixed price per milestone or a small monthly retainer for ongoing iteration. We don't run open-ended T&M because it disincentivises us from finishing.
What's the realistic outcome for Devonport businesses?
Average search time drops from 6 minutes to 12 seconds. We don't promise tenfold lifts because we don't see them outside of marketing decks.
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.
Talk to us about this
Tell us what you're trying to do and we'll reply with how we'd build it - no obligation.