Use the credentials provided to you. After sign-in, you'll see all candidate locations in your assigned area. You then pick which ones you want exact coordinates for.
test / test
AI-ranked gold targets in your assigned area. Browse all candidate locations after sign-in. Pick the ones you want exact coordinates for — pay per location, only for what you actually want.
Most targeting tools deliver a static map and walk away. This one closes the loop — every assay updates the model overnight, and the next morning's recommendations reflect what you just learned in the field.
The model ranks your AOI by expected gold-per-dollar — geology, drive distance from camp, dig cost, and offtake readiness all factor in.
Foreman pulls up the next pit on the offline tablet. GPS, depth target, expected grade, and cost all pre-populated.
Tablet captures geology, photos, voice notes, and the assay when it returns from the lab. Syncs nightly via camp Starlink.
The model updates its confidence on the surrounding ground overnight. By morning the tablet shows refreshed next-pit recommendations.
This is the same interface you get after signing in — just with preview data. Toggle map layers, switch basemaps, click any target to see the AI's reasoning, click any pit to see the assay. Press play in the next section to watch the model learn over 60 days.
Before you do any field work, the model has already ingested years of regional context — historical mineral occurrences, structural features, seismicity, settlement and access overlays, geophysical baselines, and a body of distilled regional literature. This is the starting prior you build on.
A curated database of historical mineral occurrences and prospects across your operating region. Places that produced before are statistical evidence about places that might produce next.
Records of recent seismic activity used to map active tectonic structures. Active faults often correlate with hydrothermal mineralisation; the model uses them as a structural prior.
Major settlements with population data, transport corridors, and access constraints. Used to estimate logistics costs and operational accessibility for each candidate target.
Reference deposits across the wider region used for transfer learning. The model learns what makes ground productive by studying the patterns of known producing deposits.
Geophysical grids used to detect deep structural framework — patterns that help map fault systems and lithological boundaries below soil and cover.
Decades of published regional geological research encoded as model features. The model carries the accumulated knowledge so you don't have to read it.
This is what makes the system different from a static map. Drag the timeline or press play to replay the first 60 days of synthetic operator data. The map shows pits as they were dug; the chart shows the operator's hit rate climbing past the baseline as the model learns from each new assay.
2026-05-20 · synthetic operator timeline (1-day = 1 frame at 0.3s)
Reading the chart: the gold line is the operator's cumulative hit rate on AI-recommended pits. The dashed grey line is the 18% baseline measured from blind-control pits — cells the model would not have recommended. The system is genuinely predictive when the gold line is consistently above the dashed line with low p-value. Honest signal, not a vanity metric.
The platform targets in two stages. Stage 1 uses satellite, geophysics, and historical data to compress your concession down to priority hectares. Stage 2 fuses XRF readings your team takes on those priority hectares into a refined posterior, getting you to bench-level targets. Each new pit you log keeps sharpening it.
The platform compresses a 200 km² concession down to 20–30 priority hectares using its multi-source data foundation, alteration analysis, structural features, and historical priors. No field data required at this stage.
Your team takes 50–100 handheld XRF readings per priority hectare on the AI-designed sampling grid the platform gives you. You upload the readings. The platform fuses them with the data foundation — gold and associated pathfinder elements — into a tighter posterior.
Every pit your team digs, logs, and assays feeds the Bayesian update. After six months of your operator data flowing in, the model is calibrated to your specific geology and reaches bench-level precision.
No upfront commitment to the whole area. You sign in, look at what's on offer, and decide one target at a time.
See all candidate locations in your assigned area. Each one shows the AI's reasoning: probability, expected grade range, cost estimate, geology, distance from access. Positions shown are estimates only — intentionally too imprecise to navigate to. They give you a sense of distribution and density.
Take your time. Compare targets. Talk to your geologist. Decide which ones are worth investigating with your XRF and pit budget. You don't pay anything to evaluate.
For each location you want, unlock the exact GPS. Pay per location — only for what you actually want. You then take your team to those exact points and run your XRF / dig pits / collect samples.
After you've unlocked at least one location, you can subscribe to ongoing analytical support — we keep refining the model as your XRF readings and pit results come in, deepening the picture every cycle. Available only after a first purchase; we don't start a partnership cold.
Sign in with the credentials provided to you. The dashboard loads your assigned area, your pit log, and your recommendations. No one else sees them.
Each account has its own credentials and is scoped to a specific area. Provided directly — no self-signup, no shared accounts.
The dashboard loads what's relevant to you — your AOI, your pit log, your recommendations. Other users see only their own.
Your data lives in your own encrypted tenancy on Cloudflare. Nothing shared, nothing indexed, nothing public. You can export at any time.
Nine capabilities tuned to a real Somaliland operator's day — not a research pipeline.
Each new assay updates the model's confidence on the surrounding ground and re-ranks the next targets. Cycle time from new assay to updated recommendation: under 24 hours.
Recommendations maximise expected gold per dollar — not raw probability. Cost is a model input, calibrated as your pit log grows.
QField + custom pit-log layer. MBTiles cached locally. Nightly camp Starlink sync. Works for weeks without connectivity.
Community, security, water, transport, and access factors are baked into ranking — not just geology. A high-grade target you can't reach safely is ranked accordingly.
Each target carries a logistics score alongside its geology score — distance to market, transport practicality, downstream feasibility. A high-grade target with no route to market is ranked lower than a moderate target you can actually sell.
Photograph an outcrop on the tablet. Get back: "Looks like shear-zone iron-oxide alteration. Similar to your pits #027 and #041 (2.3 and 1.8 g/t). Recommend panning 50 m N-NE."
Operator AOI never leaves your tenancy. End-to-end encrypted sync. Audit-trail exports are per-target signed CSVs — share only what the financier needs.
Every recommendation hashed, timestamped, GPS-locked, and chain-linked. The basis of the royalty calculation and your defence in any future audit.
Monthly target lists include low-probability cells the model would not otherwise recommend. Honest validation that the system is genuinely predictive, not confirming pre-existing intuition.
Sign in with the credentials provided to you. Browse your area. Pick the locations you want exact coordinates for. Pay only for what you actually want.