Events

Why AI Fails in Mining Investment: Origination, Comps, and Diligence — and What Decision-Grade Actually Takes.

Every deal you screen comes down to a handful of derived numbers — grade, reserve, recovery ratios, AISC, risk metrics. Whilst a general AI hands you a result in seconds, it never shows its working. No audit trail. No system of record. Will Coetzer and Scott North walk through where AI genuinely helps across origination, comps, and diligence, where it breaks, and how to verify what it gives you. Includes a live demo: the same mining question, the same data, put to a vanilla model and to Pulse-connected AI side by side. You'll leave with a 90-second test you can run on any AI vendor tomorrow.

Getting decision-grade answers from AI on mining data: what works, what breaks, and how to verify.

Every capital decision in mining rests on a few derived numbers — a grade, a reserve, an AISC, a recovery. The layer underneath those numbers was never industrialised. Will Coetzer and Paul Cronin examine why generic AI returns confidently wrong answers on mining data, what the token cost curve means for teams who are building on it, and what decision-grade actually requires. Includes a live demo: vanilla AI versus Pulse-connected AI on the same question, same data.

Dead Data, Live Decisions: Why mining's AI future starts with normalisation.

The geological edition. For exploration geologists and technical practitioners — what AI-native data extraction means for drill logs, resource models, and legacy archives. Will Coetzer and Scott North examine the five normalisation problems no one warns you about, and what a working geological intelligence layer actually requires. Details to follow.