Typed, ordered, inspectable
A run is a shift plan, a scheme and a graph of typed steps. Every step has an agent, a tool, a duration and a status, and the whole record is kept per circuit and lot.
Features
Capability by capability, with the limit on each.
Orebex's features are the mechanics of a system that is allowed to touch production equipment: typed runs, a policy engine, named approvals, froth and analyzer fusion, a twin, lot genealogy and an audit log. The list below is design scope, not a shipped feature list.
Illustrative scenario: Line 1 · SAG and ball circuit, rougher bank 2 · copper porphyry blend, one shift, one approval gate
Features
What the platform does
Each capability names what it does and where its limit sits.
Limits enforced at call time
Tag allow-lists, per-tag rate and magnitude limits, the operating envelope for the blend, autonomy level, shift, ore type, interlock state and water and tailings constraints are evaluated before any setpoint moves.
Named humans at the gate
Reagent-scheme changes and lot release wait for the approver the plant names. The request, the evidence and the decision are logged.
Cameras, XRF and particle size, one read
Froth vision, online analyzers and particle-size sensors fused into one live estimate of grade, recovery, froth condition and P80 per cell, with early warnings for collapse, upsets and mineralogy shifts.
Rehearse before the shift
Candidate grind, reagent and air schemes ranked on recovery, grade, energy and water before a setpoint moves. Validated targets handed to the control agents.
The record of every lot
Blend, grind record, reagent and air moves, froth and grade reads, approvals, dewatering record, assays and disposition, exportable for customer and environmental review.
Approve, correct, feed back
Metallurgists see recommendations with their evidence, approve or correct them, and those corrections train the models.
Append-only, exportable
Every agent action with source evidence, the envelope applied, confidence, predicted recovery, grade, energy, water and reagent impact, rollback path, approver and lot scope.
Every answer cites its source
Retrieval over reagent schemes, flowsheet and geometallurgy specs, mining and environmental standards and recovery procedures, tenant-isolated.
The craft, written down
Per-site recovery and grade history and per-metallurgist performance memory, versioned and scoped per tenant.
Rare cases, validated
Rare froth-collapse, feed-upset, mineralogy-shift, equipment-drift and camera-fouling variants generated to augment training and always validated against real assay distributions before promotion. Planned.
Many circuits, one policy
Model versions promoted by circuit with canary rollout and automatic fallback; group policy with per-site override on the Enterprise tier.
Run timeline · scenario
One scenario run, step by step
Every Orebex run is an ordered, inspectable sequence. This is run_4b9e27 on Line 1 · SAG and ball circuit, rougher bank 2 · copper porphyry blend. Scenario completes in 10 steps with one approval gate. P80 held at 148 µm as the blend hardened, froth stability recovered on rougher bank 2 after an air trim, a collector-dose change was approved by the shift metallurgist, predicted recovery held inside the plan, lot C-20931 released with full genealogy.
run_4b9e27
Line 1 · SAG and ball circuit, rougher bank 2 · copper porphyry blend
illustrative scenario
SUCCEEDED
-
01
ingest.shift
SUCCEEDED
0.7 s
Concentrator Orchestrator · Pulled the shift plan from the concentrator MES: copper porphyry blend B-14, P80 target 150 µm, concentrate grade at or above 25% Cu, recovery target per the geometallurgy model, energy and water budgets. Locked the operating envelope for the blend.
-
02
twin.simulate
SUCCEEDED
58 s
Concentrator Twin · Simulated 32 candidate grind, air and reagent schemes on the as-run twin for the hardening blend, ranked on predicted recovery, concentrate grade, kWh per tonne and water per tonne. Two candidates breached the thickener bed limit and were discarded.
-
03
grind.setpoint
SUCCEEDED
3 m 40 s
Crush-and-Grind · SAG-1 feed trimmed 3% and cyclone water raised as load and power signatures read a harder feed. P80 from the particle-size analyzer held at 148 µm against the 150 µm target; mill power stayed inside the energy budget.
-
04
froth.read
SUCCEEDED
continuous
Grade-and-Froth · Twelve froth cameras and the online XRF on rougher bank 2 fused at the edge. Froth stability on cells 3 and 4 fell as the blend hardened; predicted recovery drifted 0.4 points below plan. Early warning published to the control agents.
-
05
approve.human
APPROVAL
1 m 12 s
Concentrator Orchestrator · Scheme #7 raises collector dose 6% on rougher bank 2, above the standing reagent scheme. Reagent-scheme changes stay supervised on this blend, so the step was held for the shift metallurgist and approved at 07:19:44.
-
06
float.dose
SUCCEEDED
2 m 05 s
Float-and-Reagent · Approved collector dose applied with an air trim of 4% down on cells 3 and 4 inside the envelope. Froth stability recovered within eight minutes; predicted recovery returned to plan with concentrate grade read at 25.6% Cu.
-
07
classify.cyclone
SUCCEEDED
42 s
Separate-and-Classify · One cyclone brought online in cluster 1 as feed density rose with the hardness change, holding overflow size and circulating load inside the plan.
-
08
dewater.thickener
SUCCEEDED
continuous
Thicken-and-Dewater · Tailings thickener TH-2 flocculant dose trimmed as bed pressure rose; underflow density held and overflow clarity stayed inside the water-recovery target.
-
09
optimise.targets
SUCCEEDED
18 s
Throughput-and-Recovery · Whole-plant targets recomputed for the hardened blend: feed rate, P80, air and reagent targets handed to the control agents with recovery, grade, energy and water inside the budget. The losing candidates and their scores are in the run record.
-
10
lot.release
SUCCEEDED
1 m 30 s
Quality-and-Conformance · Concentrate lot C-20931 released: genealogy written (blend, grind record, reagent and air moves, froth and grade reads, approvals, dewatering record, assays as they land) and dispositioned against the concentrate spec with cited evidence for the metallurgist's sign-off.
Tool calls · scenario
The agent shows its work
Every tool invocation, argument and result is written to an append-only, human-readable log, and every reasoning step is expandable. Nothing about a run is hidden from the plant.
- 07:00:02mes.read_plan({ line: "L1", blend: "B-14", shift: "day" })
- 07:00:02ok envelope locked · P80 150 µm · grade ≥ 25% Cu · energy and water budgets
- 07:00:03twin.simulate({ candidates: 32, horizon: "1 shift" })
- 07:01:01ok best scheme #7 · recovery on plan · 2 candidates discarded (thickener bed)
- 07:01:02policy.evaluate({ scheme: 7, autonomy: "L2+" })
- 07:01:02ok 8 writes permitted · collector_dose requires human approval
- 07:01:03mill.set_feed({ tag: "SAG1.FEED_TPH", delta: "-3%" })
- 07:04:43ok P80 148 µm · power inside budget · hardness index up
- 07:04:44froth.read_bank({ bank: "R2", cams: 12, xrf: true })
- 07:18:30froth stability falling · R2 cells 3, 4 · predicted recovery −0.4 pt
- 07:18:31approval.request({ action: "collector_dose", bank: "R2", delta: "+6%" })
- 07:19:44ok approved by shift metallurgist · logged
- 07:19:45reagent.set_dose({ bank: "R2", scheme: 7 })
- 07:19:46air.set_rate({ cells: [3, 4], delta: "-4%", within: "envelope" })
- 07:27:50ok froth stability recovered · grade 25.6% Cu · recovery back on plan
- 07:27:51cyclone.set_count({ cluster: "CL-1", online: "+1" })
- 07:28:33ok overflow size held · circulating load inside plan
- 07:28:34flocculant.set_dose({ thickener: "TH-2", delta: "-2%" })
- 07:40:10ok bed pressure steady · overflow clear · water recovery on target
- 07:40:11cuopt.solve_targets({ line: "L1", objective: "recovery, grade, energy, water" })
- 07:40:29ok targets handed to 4 agents · all inside budget
- 07:40:30mes.log_lot({ lot: "C-20931", genealogy: "full" })
- 07:42:00ok scenario complete · 10 steps · lot released
Reasoning trace
Plan, thought, action, observation, exactly as the orchestrator would record it.
GoalRun the day shift on line 1 inside the plan for blend B-14: P8…
Run the day shift on line 1 inside the plan for blend B-14: P80 at 150 µm, concentrate grade at or above 25% Cu, recovery maximised, energy and water inside budget.
PlanSimulate grind, air and reagent schemes on the twin first. Lea…
Simulate grind, air and reagent schemes on the twin first. Lead with the grind so the liberation size is right before flotation sees it, then read the froth, then dose. Hold any reagent-scheme change for a human.
ThoughtThe blend is hardening. Holding feed rate would coarsen P80 an…
The blend is hardening. Holding feed rate would coarsen P80 and under-liberate; the twin predicts a 3% feed trim with more cyclone water holds P80 at the cost of a little throughput, and that protecting liberation is worth more than the tonnes.
Actiontwin.simulate(candidates=32) returns scheme #7: SAG-1 feed dow…
twin.simulate(candidates=32) returns scheme #7: SAG-1 feed down 3%, cyclone water up, collector dose up 6% on rougher bank 2, air down 4% on cells 3 and 4.
ObservationScheme #7 predicts recovery on plan, grade 25.5% Cu and energy…
Scheme #7 predicts recovery on plan, grade 25.5% Cu and energy inside budget. Two candidates with higher predicted recovery pushed the tailings thickener past its bed limit and were discarded.
ActionExecute scheme #7: eight bounded writes permitted on grind, ai…
Execute scheme #7: eight bounded writes permitted on grind, air, cyclones and dewatering; the collector-dose write routed to the shift metallurgist.
ObservationFroth stability fell on cells 3 and 4 at 07:18:30 with predict…
Froth stability fell on cells 3 and 4 at 07:18:30 with predicted recovery 0.4 points under plan. The approved dose and the air trim recovered it within eight minutes; grade read 25.6% Cu.
OutcomeScenario complete. P80 held, grade on spec, recovery on plan, …
Scenario complete. P80 held, grade on spec, recovery on plan, lot C-20931 released with full genealogy.
Where it pays
Four loops, four metrics
Orebex is not a dashboard. Each agent closes a loop a concentrator already measures in recovery points, kilowatt-hours per tonne, reagent per tonne and water per tonne. The tables show what each loop watches and what it is allowed to move.
Grade and recovery
See the froth before the assay does
Froth cameras, online XRF and particle-size sensors are fused at the edge into a live estimate of grade, recovery, froth condition and P80 per cell. Frothix predicts where recovery is heading seconds after a change and publishes early warnings the control agents act on, instead of a lab result hours later.
- Grade and recovery predicted continuously, labelled later by the assay
- Froth collapse and mineralogy shifts flagged before they cost recovery
- Every read tied to the grind, reagent and air state behind it
agent.grade_froth SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Froth condition | Camera banks, 8 to 24 per bank | Published to Floatex and Recovex |
| Grade and recovery | Online XRF plus froth model | Early warning, targets |
| P80 | Particle-size analyzer | Published to Grindex |
Grind and energy
Grind to the size flotation needs, not the curve
Mill load, power, feed rate and water are read with Frothix's P80. Grindex estimates ore hardness from the load and power signatures and moves feed, water and cyclone settings so liberation size holds as the blend changes, at the least kilowatt-hours per tonne, with every move validated on the twin first.
- Over-grinding soft ore and under-liberating hard ore both caught
- Energy per tonne priced on every move
- Grind moves rehearsed on the twin before they apply
agent.crush_grind SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| P80 | Particle-size analyzer | Feed rate, cyclone water |
| Mill load and power | Mill telemetry | Feed rate, speed where available |
| Ore hardness | Estimated from load and power | Scheme candidates ranked on the twin |
Reagent, air and froth
Hold each cell at its best point as the feed drifts
Collector, frother and depressant dosing, air and pulp level are controlled per cell against the live froth and grade read. Floatex holds the grade and recovery trade-off the plan asked for, trims air and level inside the envelope, and routes any reagent-scheme change to the metallurgist until the ore type is characterised.
- Air and level moved inside the envelope
- Reagent-scheme changes supervised by a named metallurgist
- Reagent per tonne logged per decision
agent.float_reagent SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Froth stability | Frothix per cell | Air rate, pulp level |
| Concentrate grade | Online XRF | Collector and depressant dose, under approval |
| Tailings grade | Online XRF | Frother dose, air, under approval |
Whole plant
One objective for recovery, throughput, energy and water
Grinding chases power, flotation chases recovery and sustainability chases water. Recovex solves them as one problem against the plan's constraints and hands each control agent its targets, recomputed as the feed, the constraints and the metal price change.
- Four local goals, one plant policy
- Targets handed to agents, never actuators directly
- Losing candidates and their scores kept in the run record
agent.throughput_recovery SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Recovery and grade | Frothix, assays | Targets to Floatex |
| Energy per tonne | Mill and plant meters | Targets to Grindex |
| Water per tonne | Thickener and plant meters | Targets to Thicken-and-Dewater |
Autonomy
Four levels, set per agent and per tag
A concentrator does not go from manual to unattended in one step. Orebex makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then bounded autonomy on low-risk grinding and flotation loops. Reagent-scheme changes stay supervised until the ore type is characterised.
| Level | What the agent does | What the human does | Where it sits in a pilot |
|---|---|---|---|
| L1 · Shadow | Reads froth, analyzer, particle, mill, flotation, dewatering, robot and MES signals; predicts and recommends; writes nothing | Runs the circuit as today; compares predictions to assays and metallurgist outcomes | Shadow mode, baseline measured first |
| L2 · Assist | Proposes grind, reagent, air, froth and dewatering moves with evidence, confidence, envelope and rollback path | Approves each action in the review console | Assist mode, the remainder of a 90 to 120 day pilot |
| L3 · Bounded | Executes pre-approved low-risk grinding and flotation loop moves: feed, water, air, level, flocculant, cyclones online, inside APC, DCS and envelope limits | Approves reagent-scheme changes and lot release | Graduated autonomy, after audited accuracy and ROI |
| L4 · Constrained auto-control | Supervised reagent-scheme adaptation for characterised ore types, across circuits and sites | Sets the envelope; reviews the shift record and the evaluation results | Planned; after golden-dataset evaluation, twin validation and metallurgist sign-off |
Accelerated computing
Physical AI, at the bank and the mill
Froth changes in seconds and a shift of feed is gone before the assay lands. Perception has to be local, deterministic and fast, so Orebex runs GPU inference at the plant edge and keeps training, simulation and optimisation in the cloud or on-prem.
Edge perception
8 to 24 froth cameras per bank at 15 to 30 FPS plus online XRF, particle-size, pump, level, air, reagent, density and energy streams fused at the plant edge. Sub-250 ms froth inference and local fail-safe through a network outage are the design targets. Jetson Thor is planned.
Model serving
Froth, particle and mineralogy, recovery prediction, time-series anomaly and metallurgy retrieval models behind one orchestrator at the plant edge, 20 to 60 per site as a design target, with versioned canaries and rollback.
Training
Froth segmentation, bubble velocity and stability, grade and recovery prediction, ore hardness, grind-size response, reagent response and metallurgy assistants trained on froth video, analyzer readings, telemetry and metallurgist corrections. 2,000 to 8,000 GPU-hours per commodity model family is the design target once partner data exists.
Concentrator twin
Grinding, flotation, classification and dewatering simulated as-run against as-designed before the shift. GPU comminution and DEM, flotation and geometallurgy simulation is the workload; physics-informed surrogates with Modulus are planned so schemes rank at production cadence.
Synthetic data
Rare froth-collapse, feed-upset, mineralogy-shift, equipment-drift and camera-fouling cases generated and validated against real assay distributions before promotion. 50k to 250k scenarios per commodity and circuit class is the design target.
Optimisation
Throughput, energy, water and reagent allocation and the grade and recovery trade-off solved before the shift and during upset recovery, and handed to the control agents as targets.
Robot sampling and handling
Sampling routes, reagent tote inspection and inspection rovers trained and validated in simulation before they run on site. Assistive until the safety case is proven.
GPU ETL
Daily features from froth, analyzer, mill, flotation, dewatering and genealogy telemetry for retraining, drift detection and recovery, energy, water and reagent benchmarks.
Guardrails
An agent that can move a reagent pump needs a leash
Orebex writes to production equipment. Every capability is scoped, every write is policy-checked against the operating envelope, and every action is written to an append-only audit log the plant owns.
- Bounded action space. Each agent writes only to an explicit tag allow-list, inside per-tag rate and magnitude limits and the operating envelope for the blend.
- Policy engine before every write. Autonomy level, shift, ore type, interlock state, water and tailings constraints and metallurgist policy are evaluated before a setpoint moves.
- Human-in-the-loop gates. Reagent-scheme changes and lot release wait for a named approver. Robotics stays assistive until the site safety case is proven.
- Immutable audit log. Append-only and exportable. Every action records source evidence, the envelope applied, confidence, estimated recovery, grade, energy, water and reagent impact, rollback path, approver and lot scope.
- Hard fallback. Loss of the edge node, the network or a model returns control to the APC or DCS last known-good state. Interlocks are never in Orebex's path, and the edge runs fail-safe through a network outage.
- Tenant and ore-body isolation. Ore-body data, geometallurgy models, reagent schemes and recovery records never cross a customer boundary. On-prem and edge deployment is available for remote sites.
Compliance posture
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I | Cloud control plane | QUEUED Planned, first 6 months |
| SOC 2 Type II | Cloud control plane | QUEUED Planned, 6 to 12 months |
| SSO and RBAC | Console and approvals | QUEUED Planned, 6 to 12 months |
| Environmental and water assurance packages | Recovery, energy, water and tailings evidence | QUEUED Planned, 6 to 12 months; not a certification claim |
| Standards-cited reasoning | ISO, ICMM, tailings and water governance documents | RUNNING In the design, every answer cites its source |
| Per-tenant and ore-body isolation | Ore data, schemes, models, memory | RUNNING In the design from day one |
| On-prem and plant-edge deployment | Remote and IP-sensitive sites | RUNNING Design option |
FAQ
Straight answers
The questions processing managers, metallurgists and sustainability leads ask in the first meeting.
Yes, but only within an explicit tag allow-list with per-tag rate and magnitude limits, inside the operating envelope for the blend, and only at the autonomy level your plant has set. Design partners start in shadow mode, where Orebex writes nothing. Reagent-scheme changes stay supervised by a named metallurgist until the ore type is characterised.
Control returns to the APC or DCS last known-good state. Orebex is a supervisory layer on top of the control systems and interlocks you already run, never a replacement for them, so an outage degrades the circuit to its current way of running, not to a stop. The edge is designed to run fail-safe through a network outage.
Advisory recommendations start from the twin and the shift plan in the first weeks. Froth, grade, recovery and grind-response prediction improve as circuit history and assay-labelled outcomes accumulate per ore type. The compute plan sizes training at 2,000 to 8,000 GPU-hours per commodity model family once partner data exists, a design target.
Only if you choose cloud training. Ore-body data, geometallurgy models, reagent schemes, process models and recovery records are isolated per tenant and never used to train another customer's models. A fully on-prem deployment at the plant edge is available for remote and IP-sensitive sites, and federated learning across sites is planned and waits on data-rights agreements.
You are, the same as with any control strategy, which is why every write is policy-checked, bounded, logged and reversible, and why anything above your risk threshold waits for a named approver. The audit log records the request, the evidence, the envelope applied and the human decision.
A paid pilot of 90 to 120 days on one grinding or flotation circuit, scoped to a single wedge with a success metric written into the order form: recovery gain, energy per tonne saved, water reduction or reagent per tonne. The first weeks baseline recovery, energy and water in shadow mode from your own assays and meters.
Get started
See the features on one circuit
Start with one grinding or flotation circuit and one measurable baseline. A paid pilot on froth-vision recovery control, grind-size energy or reagent dosing shows the number before you commit further.