AI and machine learning in Dunedin

What AI and machine learning means here

The core of what we build. Models that read your documents, answer in your own language and take the repetitive work off your team, running against your systems rather than a demo dataset.

• Agents that work inside your existing tools, not beside them
• Retrieval over your own documents, with the source cited on every answer
• Fine tuning and evaluation against tasks your team actually does
• Human review on anything that leaves the building

Built on: Claude OpenAI open weight models vector search Cloudflare Workers

How we would approach it

We scope narrow, ship a working pilot, then harden it into production. The first slice is the highest-leverage workflow for your Dunedin business, so value lands before the build is finished.

1. Find the one workflowWe look for the job costing Dunedin businesses the most hours or the most leads, and deliberately ignore the rest for now.
2. Ship a working sliceA narrow version goes into production in weeks, against real work, so the value shows up before the build is finished.
3. Prove it, then widenWe measure it against what the work cost before. If it does not pay for itself, we say so rather than scaling it.
4. Harden and hand overLogging, fallbacks and a real handover, so it keeps running when we are not in the room.

FAQ

Do you actually work on AI and machine learning?

The core of what we build. Models that read your documents, answer in your own language and take the repetitive work off your team, running against your systems rather than a demo dataset.

What does this look like for a Dunedin business?

Dunedin pairs a strong university research culture with practical southern businesses. AI here means proven tools, not hype. We scope one workflow, ship it to production, and prove the return before expanding.

Where do you start?

With the workflow costing the most time or the most leads. Most teams do not need a bigger model, they need one wired into the system where the work already happens.

Is this a talk or a build?

Both, depending on what you need. We speak on AI and machine learning, and we build the systems behind it. The advice is the same either way, and it is free of charge until there is a scope to quote.