Portfolio

AI, built for production.

Demos are easy. Systems that hold up under real traffic, real data and real governance are not. The examples below show the kind of applied AI we design, ship and operate — the problems we take on and the way we approach them.

ℹ️ These are representative examples. Client names are withheld under NDA, and the figures shown are indicative of the kind of outcomes these systems are built to achieve.
Live
Systems in production
APAC
Delivery footprint
7
Industries served
99.9%
Operating uptime
Featured — Automotive · New Zealand

Flagship work in the Asia-Pacific automotive sector

A large share of our production deployments serve automotive businesses across APAC, and New Zealand especially — from national dealer groups to used-import specialists.

RAGAgentic AIAutomotiveNew Zealand

Dealer group sales & compliance assistant

Challenge — A New Zealand dealer group with sites nationwide was drowning in fragmented vehicle data: OEM spec sheets, used-import histories from Japan, finance and insurance products, and shifting Clean Car and NZTA compliance rules. Sales staff couldn't answer buyer questions confidently, and compliance risk sat with individual salespeople.

Solution — We built a grounded RAG assistant over inventory, vehicle history and regulation, plus an agentic layer that checks Clean Car obligations, drafts finance-ready summaries and flags import-compliance gaps — all tuned for right-hand-drive, used-import realities and hosted with NZ data residency.

🚗 2019 import market: NZ RHD
{ "clean_car": "fee: $2,300", "NZTA": "compliant", "finance_ready": true }
sites · 14residency ✓latency · 210ms
Results
14
Dealership sites live
Faster buyer question turnaround
90%
Compliance checks automated
NZ
Data residency, end to end

“They understood the New Zealand market — used imports, Clean Car, the lot. That local knowledge is why it actually works on the floor.” — General Manager, national dealer group

RAG & KnowledgeFinServ

Regulatory knowledge assistant

A cited RAG assistant sitting on top of 120k compliance documents — so a lending team stops hunting through PDFs and gets grounded answers with sources.

Challenge

Compliance analysts spent hours tracing rules across regulator circulars, internal policy and product manuals. Answers were inconsistent, hard to audit, and impossible to scale as the rulebook changed weekly.

Solution

We built a retrieval pipeline with section-aware chunking, hybrid semantic + keyword search and a re-ranking stage, then constrained the model to answer only from retrieved passages — every sentence carries an inline citation to the source clause. A nightly ingestion job keeps the index current, and an evaluation harness gates each release against a labelled question set.

Results
68%
Cut in research time per query
120k
Documents indexed & searchable
94%
Answer accuracy on eval set

“We stopped guessing where a rule lived. The assistant hands us the clause and the citation — audit trail included.” — Head of Compliance, lending platform

Agentic AILogistics

Autonomous operations agent

A tool-using agent that triages shipment exceptions and drafts resolutions across five internal systems — with a human approving anything that moves money.

Challenge

Ops coordinators juggled a TMS, a WMS, a carrier portal, email and a ticketing tool to clear each stuck shipment. Context-switching was the job; exceptions piled up overnight and SLAs slipped.

Solution

We designed a planner-executor agent with typed tools for each system, strict input/output schemas and a policy layer that decides what it may do autonomously versus escalate. It reads the exception, gathers state across systems, proposes a fix, and either executes low-risk actions or routes a pre-filled resolution to a human. Every step is logged and replayable.

Results
73%
Exceptions cleared without a human
18 min
Median resolution, down from 3.5h
0
Unauthorised money-moving actions

“It does the boring detective work across five tools and hands us a decision. My team runs the exception queue, not the other way round.” — Director of Operations, freight network

Generative AIeCommerce

Product content engine

A generative pipeline that turned a spreadsheet of raw specs into 40k on-brand product descriptions — with human review kept exactly where it earns its keep.

Challenge

A fast-growing catalogue shipped with thin, inconsistent copy. Manual copywriting couldn't keep pace with new SKUs, and outsourced batches drifted off-brand and off-tone.

Solution

We built a structured generation pipeline that pulls attributes per SKU, generates copy against a brand voice guide and per-category templates, then runs automated checks for tone, banned claims and SEO structure. Anything low-confidence or high-visibility is queued for a human editor — the rest publishes on approval, with every generation versioned for audit and rollback.

Results
40k
On-brand descriptions generated
Faster catalogue turnaround
+22%
Organic traffic to product pages

“Our editors stopped writing from scratch and started approving. Same voice on every page, at a scale we couldn't touch before.” — Head of Content, online retailer

Generative AIRAGHealthTech

Clinical documentation copilot

A copilot that drafts visit notes from the consultation and cites the clinical guideline behind each recommendation — giving clinicians their evenings back.

Challenge

Clinicians lost hours a day to documentation, and note quality varied. Any AI here had to be grounded, conservative and never invent a clinical claim — accuracy and traceability were non-negotiable, and nothing could be autonomous.

Solution

We combined structured note generation with retrieval over an approved guideline library. The copilot drafts a SOAP note from the encounter, grounds every recommendation in a cited guideline, flags anything uncertain, and hands a full draft to the clinician to edit and sign. Nothing enters the record without a human signature, and every draft is evaluated against clinician-reviewed gold notes.

Results
2.1h
Saved per clinician, per day
96%
Drafts signed with minor edits
100%
Recommendations guideline-cited

“It writes the first draft, I stay in control of the record. The citations are what got it past our clinical governance board.” — Chief Medical Officer, digital health provider

Agentic AIRAGSaaS

Support deflection & triage

A RAG-backed agent that answers what it can from the docs and routes the rest — with priority, product area and a suggested reply already attached.

Challenge

A rising support volume buried the team in repetitive questions, while genuinely urgent tickets waited in the same queue. Canned macros felt robotic and mis-routing sent issues to the wrong pod.

Solution

We deployed an agent that first attempts a grounded answer from the help centre and changelog, citing its sources. When it can't resolve confidently, it classifies the ticket by product area and urgency, drafts a reply for an agent to approve, and routes it to the right team. Confidence thresholds and an eval loop keep deflection honest — it never bluffs an answer it can't ground.

Results
41%
Tickets deflected at first touch
–34%
Median first-response time
92%
Routing accuracy to correct team

“Deflection that doesn't annoy customers, plus triage that actually lands tickets in the right place. Our CSAT went up, not down.” — VP Customer Experience, B2B SaaS

RAG & KnowledgeLegalOps

Contract intelligence

Clause extraction and risk flagging across thousands of contracts — turning a shared drive of PDFs into a queryable, reviewable knowledge base.

Challenge

A legal team faced renewal deadlines and audit requests with no way to know which contracts held which terms. Manual review of thousands of agreements was slow, and non-standard clauses slipped through until they became a problem.

Solution

We built an extraction pipeline that identifies parties, key dates, liability caps, indemnities and termination terms, then flags clauses that deviate from the team's playbook. A retrieval layer lets a lawyer ask natural-language questions across the whole portfolio and jump straight to the governing clause — every extraction links back to its exact location for human verification.

Results
7,400
Contracts processed & indexed
85%
Faster first-pass review
310
High-risk clauses surfaced early

“We went from ‘we think that clause is in there somewhere’ to a searchable answer with the paragraph attached. Renewals stopped ambushing us.” — General Counsel, enterprise software firm

Where we work

Industries we serve

Regulated, high-throughput teams where accuracy, auditability and uptime are not optional.

FinServ HealthTech Logistics LegalOps eCommerce SaaS GovTech
The bar we hold

How we measure success

We don't call a system done because a demo impressed someone. We call it done when it moves a number the business already tracks — and keeps moving it in production.

  • A baseline is agreed before we build, so “better” is measurable, not a feeling.
  • Every model output is evaluated against a labelled test set on each release.
  • Accuracy, latency and cost are tracked together — no one metric wins alone.
  • Human-in-the-loop stays wherever a wrong answer is expensive or unsafe.
  • Grounded answers carry citations, so results are auditable, not just plausible.
  • Observability, drift monitoring and alerting ship with the system, not after it.
  • We report the honest numbers — including where AI is the wrong tool for the job.
In their words

The kind of feedback we build for

Illustrative of the outcomes and working relationship our clients value.

“Netatum was the first team that talked about evaluation before they talked about models. That's why the thing actually works six months later.”

VP Engineering, lending platform

“They shipped a working proof-of-value in weeks, then were honest about what to automate and what to leave to people. Rare and refreshing.”

Director of Operations, freight network

“The citations are what won over our governance board. We could see exactly where every answer came from. That built the trust to roll it out.”

Chief Medical Officer, digital health provider

Let's build

Want your project on this page next?

Bring us the workflow, the data and the metric you want to move. We'll tell you honestly whether AI is the right tool — and if it is, we'll ship it.