Insights

Research & Field Notes

Applied AI R&D, engineering practice, and lessons from building intelligent systems — written by the MarcTech team.

Research1 Sept 2026

Small-Model Economics: Why the Frontier Model Isn't Always the Right Call

When a smaller model beats the frontier model in production. Cost, latency and failure-mode trade-offs from applied AI R&D in Australia, finance to voice.

6 minRead →
Research6 Aug 2026

CPS 230 When Your Service Provider Is an AI System

APRA's operational risk standard never mentions artificial intelligence. It doesn't need to. If your AI sits inside a bank's critical operation, the obligations arrive through the contract — and the transition period has already expired.

8 minRead →
Research5 Aug 2026

AI and the Best Interests Duty: Where Automation Stops in Mortgage Broking

No Australian law addresses AI use by mortgage brokers. That doesn't mean the question is open — the best interests duty already answers most of it, and a privacy deadline in December closes the rest.

8 minRead →
Field Notes4 Aug 2026

Prompt to Production: Shipping AI Features Without Breaking Things

A prompt that works in a playground is not a shipped feature. Here's the internal pipeline we use to take AI from a working prompt to something safe to run in production.

7 minRead →
Research2 Aug 2026

When Not to Use AI: A Decision Framework

The discipline that separates good AI engineering from hype is knowing when not to use it. A practical framework for deciding when a model is the wrong tool for the job.

6 minRead →
Field Notes31 July 2026

The Integration Layer: Turning Fragmented Systems Into One Intelligence Surface

Most business AI value isn't blocked by the model. It's blocked by data trapped in disconnected systems. The unglamorous integration layer is where intelligence becomes possible.

6 minRead →
Research29 July 2026

Evaluating Language Models for Regulated Work: Accuracy, Auditability, Cost

In finance and professional services you can't ship an AI feature on vibes. Evaluating models for regulated work means measuring accuracy, auditability and cost as one system.

7 minRead →
Field Notes27 July 2026

Knowing When to Hand Off: Designing the Escalation Path in an AI System

The hardest decision in an AI product isn't what the system does — it's when it should stop and get a human. Designing that escalation path well is where trust is built.

6 minRead →
Research25 July 2026

Grounding Language Models on Proprietary Data: Retrieval That Doesn't Drift

Language models hallucinate on internal data because they were never trained on it. Grounding them reliably is a retrieval problem, not a model problem. Here's how we approach it.

6 minRead →
Research23 July 2026

Applied AI R&D: Shipping Production Intelligence Without a Research Lab

Most Australian firms don't need a research lab to do real AI R&D. They need a disciplined loop that turns open questions into shipped systems. Here's the applied approach we use.

6 minRead →
Field Notes23 July 2026

The Last 200 Milliseconds: Engineering Latency in Real-Time Voice AI

A natural phone conversation lives or dies on response time. Here's how we engineer the latency budget for a real-time voice AI system — where the milliseconds go, and how to win the ones that matter.

7 minRead →