Platform

Perception at the plant edge. Reasoning above it. Safety around both.

The Nitreum platform is a plant-edge inference runtime, a complex orchestrator with a policy engine, the Nitrotwin twin, and a cloud or on-prem training loop. Agents perceive from cameras, online analyzers, emissions sensors, the historian and the DCS, predict conversion, concentration, granule quality, nutrient content, energy, emissions and off-spec risk, and act through guarded connectors inside safety envelopes.

Plant edge + cloud or on-premEleven agents, one orchestratorAudit log from day one

run_scn_01 · agent graph · scenario 10 nodes · 1 approval gate
01 · orchestrator order.receive ✓ SUCCEEDED 02 · orchestrator twin.simulate ✓ SUCCEEDED 03 · reform_synth loop.control ✓ SUCCEEDED 04 · react_evap evaporate.control ✓ SUCCEEDED 05 · granulate granulate.control ✓ SUCCEEDED 06 · coat_condition condition.cool ✓ SUCCEEDED 07 · defect_inspect inspect.granules ✓ SUCCEEDED 08 · orchestrator approve.human ◆ APPROVAL 09 · blend_bag blend.bag ✓ SUCCEEDED 10 · quality_conf release.genealogy ✓ SUCCEEDED

Illustrative scenario: Complex run · one urea granulation campaign from synthesis gas to bagged lot · ammonia loop, urea synthesis and evaporation, granulator, dryer and cooler, NPK bagging line. Not a measured run.

Architecture

The loop, end to end

Perceive feed, synthesis gas, melt, granule and product; plan synthesize, evaporate, granulate, blend and inspect; run with adaptive process control; sense and predict conversion, concentration, granule quality, nutrient and emissions; optimize yield, energy, off-spec, emissions and takt; flag off-spec and safety risk; log; retrain.

01 · Sense

Plant-edge ingestion

DCS, APC, MES and historians, PLCs, online nutrient, moisture and concentration analyzers, cameras, emissions sensors, robot telemetry, lab assays and quality systems are normalized into a time-series store, an object store, a vector index and an audit ledger at the edge.

02 · Infer

Edge models

Fine-tuned granule size, shape, dust and caking vision, analyzer fusion, reforming and ammonia-loop, granulation and energy and emissions models, plus time-series prognostics for compressors, reactors and granulators, served with TensorRT and Triton.

03 · Reason

Complex orchestrator

Retrieves product and process specs, safety and emissions procedures and standards with citations, asks the agents for recommendations, runs constraint and safety-envelope checks, rehearses high-impact moves on Nitrotwin and applies the autonomy policy.

04 · Act and learn

Guarded write-back

Approved actions go back through approved DCS and APC interfaces inside tag, rate and magnitude limits, never to a safety system. Every action and every engineer correction becomes a labeled event for the training loop.

Run timeline

A run is the unit of work

Every Nitreum run is an ordered, inspectable sequence. This is run_scn_01, an illustrative scenario: Complex run · one urea granulation campaign from synthesis gas to bagged lot · ammonia loop, urea synthesis and evaporation, granulator, dryer and cooler, NPK bagging line. Scenario complete · lot inside spec · one human approval on the ammonia loop.

run_scn_01 scenario · not measured SUCCEEDED
  1. 01 order.receive SUCCEEDED 0.8 s

    Complex Orchestrator · Pulled the grade spec, the nutrient target, the granule spec for size distribution, hardness and moisture, the emissions permit limits, the safety-instrumented envelope and the standing changeover window from the plant MES and the historian; locked the target envelope for the campaign.

  2. 02 twin.simulate SUCCEEDED 41 s

    Complex Orchestrator · Simulated 24 candidate loop, evaporation, granulation and sequencing plans on the Nitrotwin as-produced complex twin; ranked them on conversion, energy per tonne, predicted granule distribution, recycle ratio, emissions margin and takt, and discarded every candidate that thinned the safety or permit margin.

  3. 03 loop.control SUCCEEDED continuous

    Reform-and-Synthesize · Held ammonia-loop conversion and reformer temperature inside the approved envelope from live loop telemetry and the conversion model, trimming setpoints toward the lowest energy per tonne the plan allowed; purge and trip settings were read, never written.

  4. 04 evaporate.control SUCCEEDED continuous

    React-and-Evaporate · Held urea melt concentration at the granulation target from the online concentration analyzer and the evaporation model, moving evaporator setpoints inside the recipe window rather than waiting for the next lab assay.

  5. 05 granulate.control SUCCEEDED continuous

    Granulate-and-Prill · Tuned recycle ratio, spray and bed temperature from the live Granvis size distribution and moisture signal, each move validated on the twin first; the granule distribution stayed inside the spec band while recycle trended down.

  6. 06 condition.cool SUCCEEDED continuous

    Coat-and-Condition · Held dryer and cooler outlet temperature and moisture inside the storage window and set the anti-caking coating rate to the predicted caking risk for the product and the season; nothing moved outside the conditioning envelope.

  7. 07 inspect.granules SUCCEEDED continuous

    Defect-and-Inspect · 12 camera streams at the plant edge: granule size and shape, dust, caking precursors and broken prills on the granulator discharge, cooler and bagging belts; two dust spikes were attributed to one spray nozzle and Granulate-and-Prill corrected it inside its window.

  8. 08 approve.human APPROVAL 2 m 14 s

    Complex Orchestrator · The lowest-energy candidate wanted a purge-rate change on the ammonia loop beyond the bounded envelope. Held for the shift process engineer and the process-safety approver, who approved a smaller step with the safety-instrumented envelope untouched and a tighter review interval.

  9. 09 blend.bag SUCCEEDED continuous

    Blend-and-Bag · Held the NPK blend ratio to the nutrient spec from Granvis nutrient sensing, checked segregation on the belt and held bag weight to target; three overweight bags were attributed to one dosing gate and the gate was trimmed inside the approved window.

  10. 10 release.genealogy SUCCEEDED 1 m 10 s

    Quality-and-Conformance · Lot released: conversion and energy per tonne, melt concentration, granule distribution, hardness and moisture, nutrient assay, emissions readings, inspection events, bag weights and every human decision written to the lot genealogy and checked against spec and permit.

Tool calls

The agent shows its work

Every tool invocation, argument and result is written to an immutable, human-readable log, and every reasoning step is expandable. Nothing about a run is hidden from the plant. The log below is the scenario run, not a measured one.

tool-call stream · run_scn_01
  1. 05:10:02mes.read_order({ campaign: "U-4471", grade: "UREA-46", pack: "BAG-50" })
  2. 05:10:02ok grade spec locked · permit limits v4 · SIS envelope read-only
  3. 05:10:03historian.read_baseline({ unit: "AMM-1", window: "30d" })
  4. 05:10:03ok energy per tonne baseline loaded · catalyst age noted
  5. 05:10:04twin.simulate({ candidates: 24, horizon: "campaign" })
  6. 05:10:45ok best plan #9 · permit margin held · lowest energy per tonne
  7. 05:10:46policy.evaluate({ plan: 9, stage: "bounded" })
  8. 05:10:46ok 7 writes permitted · 1 write requires human approval
  9. 05:10:47dcs.write_setpoint({ tag: "AMM1.LOOP_T", basis: "conversion+energy" })
  10. 05:14:30ok conversion on target · energy per tonne trending down
  11. 05:20:00analyzer.read_concentration({ unit: "EVAP-2" })
  12. 05:20:00ok melt concentration inside window · evaporator setpoint held
  13. 05:31:12granvis.read_distribution({ unit: "GRAN-1", metric: "size_moisture" })
  14. 05:31:12ok distribution inside spec band · recycle ratio trimmed after twin check
  15. 05:31:13vision.stream({ cameras: 12, models: ["size_shape", "dust", "caking", "bag_defect"] })
  16. 06:02:48dust spike · cooler belt · attributed to spray nozzle 3
  17. 06:02:49defect.attribute({ event: "dust_spike", cause: "granulator.nozzle_3" })
  18. 06:02:49ok granulate notified · spray trimmed inside window · second spike, then clean
  19. 06:02:50dcs.write_setpoint({ tag: "COAT1.RATE", basis: "moisture+caking_risk" })
  20. 06:02:50ok coating rate set · moisture inside storage window
  21. 06:02:52approval.request({ action: "loop.purge", reason: "beyond bounded envelope" })
  22. 06:05:06ok approved by the shift process engineer and the process-safety approver · smaller step · SIS untouched
  23. 07:40:10plc.write_setpoint({ tag: "BLEND1.RATIO", basis: "nutrient+segregation" })
  24. 07:40:10ok nutrient ratio on spec · bag weight on target · gate 2 trimmed
  25. 09:18:30mes.release_lot({ campaign: "U-4471", genealogy: "full" })
  26. 09:19:40ok lot released · scenario complete

Reasoning trace

Goal, plan, thought, action, observation, exactly as the orchestrator would record it.

GoalRun campaign U-4471 from synthesis gas to bagged lot: ammonia …

Run campaign U-4471 from synthesis gas to bagged lot: ammonia loop at target conversion per unit of energy, melt at exact concentration, granules on spec with minimum dust and recycle, conditioned for storage, bagged to weight and released with full genealogy and emissions readings.

PlanSimulate the whole campaign on the twin first. Lead with conve…

Simulate the whole campaign on the twin first. Lead with conversion so evaporation gets the right melt and the granulator gets the right concentration. Verify emissions and the safety envelope continuously. Let the granulator chase the size band only inside the approved window; hold any ammonia-loop move beyond the envelope for a human.

ThoughtThe standing practice runs the loop and the granulator on fixe…

The standing practice runs the loop and the granulator on fixed setpoints and corrects after the assay. With live conversion, concentration and granule distribution the loop and the granulator can sit at target. The saving is energy, recycle and dust, not safety margin: the safety-instrumented envelope and the permit limits are never candidates for optimization.

Actiontwin.simulate(candidates=24) → plan #9: conversion on target, …

twin.simulate(candidates=24) → plan #9: conversion on target, melt concentration on spec, granule distribution inside the band, permit margin unchanged, lowest predicted energy per tonne.

ObservationPlan #9 wants a purge-rate change on the ammonia loop beyond t…

Plan #9 wants a purge-rate change on the ammonia loop beyond the bounded envelope. The policy engine routes that single move to the shift process engineer and the process-safety approver and permits the other seven writes.

ActionExecute plan #9 at the bounded stage: loop temperature, evapor…

Execute plan #9 at the bounded stage: loop temperature, evaporator, granulator, coating and blend writes proceed; emissions are verified continuously; the purge move waits.

ObservationApproval granted at 06:05:06 with a smaller step and the safet…

Approval granted at 06:05:06 with a smaller step and the safety-instrumented envelope untouched. Two dust spikes were attributed to spray nozzle 3 and corrected by Granulate-and-Prill inside the approved window.

OutcomeScenario complete. The lot is released with conversion and ene…

Scenario complete. The lot is released with conversion and energy per tonne, melt concentration, granule distribution, nutrient assay, emissions readings and the human decision in the genealogy. No measured plant result is claimed; this is the run the platform is designed to execute.

Plant edge

The edge node is the product

A fertilizer complex is remote, runs continuously and often restricts cloud links, so Nitreum's inference runs beside the equipment and keeps working if the cloud does not.

  • Local inference. Granule, dust, caking and bag-defect decisions at 50 to 120 ms p95, as a design target, on Jetson Orin or Thor and plant-edge GPU servers.
  • Deterministic stream fusion. DeepStream and Holoscan fuse 8 to 40 camera feeds per unit with analyzer, historian, emissions, acoustic and thermal streams at 1 to 10 Hz for control-grade context.
  • Model routing. Triton and NIM serve vision, time-series, RAG and process-reasoning models, routed by grade, unit and site, with canary deployment. NVIDIA AI Enterprise is the planned runtime for regulated deployments.
  • Fails to existing control. If the node, the network or a model stops, the plant keeps running on its DCS, APC and safety systems.
  • Tenant-scoped memory. Per-site yield, quality and energy history and per-engineer corrections stay with the site.

What runs where

Workloads by location
WorkloadWhere
Granule vision, analyzer and emissions fusion, control inferencePlant edge
Orchestrator, policy engine, audit logPlant edge
Training and fine-tuningDGX/HGX, cloud or on-prem GPUs (planned)
Nitrotwin twin and process CFDOVX-class or cloud GPUs (planned)
Synthetic rare-upset generationGPU cloud (planned)
RAPIDS analytics, model governanceCloud or private cloud
Digital twin

As-produced, not as-designed

Nitrotwin couples physics-informed surrogates for the ammonia loop, evaporation, granulation, blending and emissions with the live plant state, so a synthesis, granulation and sequencing plan is rehearsed before tonnes, energy and CO2 are spent.

Before the run

Plan and envelope search

Candidate plans are ranked on conversion, energy per tonne, predicted granule distribution, recycle ratio, emissions margin and takt. Anything that thins the safety or permit margin is discarded before it is ever proposed.

During the run

Setpoints for the agents

Optimized setpoints are handed to Synthex, Granulex and Blendex. Distilled surrogates run at the edge for on-line envelope checks.

After the run

Calibration

Twin-versus-actual drift is measured on every lot and recalibrates the surrogates. Validated synthetic rare upsets harden every model.

Nitrotwin in detail

Accelerated computing

Physical AI, at the plant edge

A fertilizer complex is remote, continuous and often restricted from cloud links, so perception has to be local and fast. Nitreum runs GPU inference at the plant edge and keeps training, simulation and optimization in the cloud, in a private cloud or on-prem. Items marked planned are on the roadmap, not running.

Jetson Orin / Thor · DeepStream · Metropolis · TensorRT · Holoscan

Edge perception

8 to 40 camera feeds per unit through DeepStream pipelines and TensorRT detectors and segmenters for granule size and shape, dust, caking, broken prills and bag defects; Holoscan fuses vision with analyzer, historian, emissions, acoustic and thermal streams at 1 to 10 Hz. Design target: 50 to 120 ms p95 inference.

Triton · NIM · NVIDIA AI Enterprise

Model serving

Vision, time-series, RAG and process-reasoning models behind one orchestrator, with canary deployment and per-site routing. NVIDIA AI Enterprise is the planned runtime for regulated deployments.

DGX / HGX · NeMo · Retriever · Guardrails

Training and reasoning (planned)

Granule vision, time-series prognostics and NeMo process-reasoning models fine-tuned from labeled images, process histories, engineer corrections and event logs. Design target: 2 to 5 model families and 500 to 2,000 GPU-hours per cohort.

Omniverse · Modulus · OVX

Digital twin (planned)

The Nitrotwin complex twin: physics-informed surrogates for the ammonia loop, evaporation, granulation, blending and emissions, with GPU-accelerated process and CFD sweeps run before a plant change.

Cosmos · Omniverse Replicator

Synthetic data (planned)

Rare dust, caking, wet-granule, broken-prill, lighting, belt-contamination, emissions-spike and upset scenarios generated and labeled as synthetic, validated against real plant events before a model learns from them.

cuOpt

Optimization

Throughput, recycle balancing, energy and emissions allocation and grade-changeover sequencing under constraints, recomputed on the GPU when the complex is disrupted.

RAPIDS

Data engineering

ETL over historian, quality, emissions and vision data for feature generation, quality correlation and cross-site benchmarks on the GPU.

Isaac · Jetson

Robotic handling

Bag palletizing, bulk loading, materials handling and inspection rovers, with perception and motion policies built and validated in simulation before they move a pallet.

Autonomy

Four stages, set per loop

A plant does not go from manual to bounded control in one step. Nitreum makes the stage explicit per loop, auditable and reversible at any time, and some decisions never leave the person. On the ammonia side every stage is safety-gated.

Autonomy stages and the human role at each
StageWhat the agent doesWhat the person doesWhen
ShadowPredicts conversion, concentration, granule quality, nutrient content, energy, emissions and off-spec risk; writes nothingRuns the plant as today; compares predictions to assay, historian and engineer outcomesFirst phase with every design partner
AssistRecommends bounded loop, evaporation, granulation, coating and blend moves with the evidenceA process engineer approves or rejects each oneAfter accuracy is proven against the baseline
BoundedWrites low-risk granulation, conditioning and blending setpoints inside documented recipe, quality, safety, emissions, equipment and rollback limitsApproves anything above the limits and every ammonia-loop move beyond the envelope; reviews the shift recordAfter the safety and ROI gates agreed up front
ExceptionsEscalates anything outside its envelope, safety-adjacent moves and release decisionsAlways decides these; the agent never doesPermanent
Multi-agent handoff

Agents negotiate, they do not collide

Two agents will want the same actuator. The orchestrator arbitrates on the run goal, with process safety above everything, and the handoff is logged like any other step.

Contested move: ammonia-loop purge rate

  1. 01yield_takt.request(purge −8%) SUCCEEDED0.2 s

    Yield-and-Takt wants a lower purge rate on the ammonia loop so less hydrogen is lost and energy per tonne falls for the campaign.

  2. 02reform_synth.request(purge hold) SUCCEEDED0.2 s

    Reform-and-Synthesize requires the purge rate that keeps inerts inside the loop envelope the process-safety review approved. That envelope is not an optimization variable.

  3. 03orchestrator.arbitrate SUCCEEDED0.4 s

    Process safety outranks energy under every run goal. The envelope wins the actuator; the request for a lower purge is logged with its score and the reason it lost, and a smaller step is routed to a named approver.

  4. 04yield_takt.handoff(resequenced) SUCCEEDED95 s

    Yield-and-Takt recovers the energy target by shifting the dryer duty and the changeover window instead. Takt is met without touching the loop envelope.

Arbitration rules

  • Run goal first. Every request is scored against the declared goal, not against the requesting agent's local objective.
  • Process safety outranks everything. A safety-instrumented envelope or a permit limit is never an optimization variable. An ammonia-loop upset is a safety event; a takt miss is a schedule.
  • Time-boxed ownership. An agent holds a contested actuator for a bounded window, then must re-justify.
  • Everything is logged. The losing request, the score and the reason all appear in the run record.
  • Deadlocks escalate to a human rather than resolving by timeout.

See the agent roster

Agent roster

Eleven agents and an orchestrator

Each agent owns a stage of the complex, a bounded tool set and a measured outcome. They negotiate for shared actuators through the orchestrator, never directly. Nine ship inside the five products; the conformance agent arrives with the Complex tier, and the knowledge agent has no write tools at all.

agent.reform_synth

Reform-and-Synthesize

Reforming, the ammonia loop, conversion, temperature, pressure, catalyst duty, energy

Reads conversion, loop temperature and pressure, purge and compressor state against the approved envelope and holds the reformer and the high-pressure ammonia loop at target conversion per unit of energy, inside safety-gated limits that never touch a trip setting.

dcs.read_looploop.predict_conversiondcs.write_setpoint(loop)

Design scope: conversion held, energy per tonne down, no upsets

Ships in: Synthex

agent.react_evap

React-and-Evaporate

Urea and nitrate reaction, concentration, evaporation

Holds urea or nitrate reaction and the evaporation train at exact melt concentration before granulation, trimming reactor and evaporator setpoints inside the recipe window instead of correcting after a lab assay comes back.

analyzer.read_concentrationevap.predictdcs.write_setpoint(evap)

Design scope: concentration on spec, evaporation energy minimized

Ships in: Synthex

agent.granulate

Granulate-and-Prill

Granulation and prilling, recycle ratio, size, roundness, hardness, moisture

Uses Granvis size-distribution and moisture state to tune recycle ratio, binder and spray, bed and drum conditions and air flow so granules leave at target size, roundness, hardness and moisture with less dust and less recycle, every move validated on the twin first.

granvis.read_distributiontwin.validate(move)dcs.write_setpoint(granulator)

Design scope: granule spec held, dust and recycle down

Ships in: Granulex

agent.coat_condition

Coat-and-Condition

Drying, cooling, coating, anti-caking conditioning, storage stability

Holds dryer and cooler outlet temperature and moisture, then sets coating and anti-caking conditioning rates to the product's storage window, so granules that were right at the granulator are still right in the bag and the pile.

dcs.read_dryer_coolercoat.predict_cakingdcs.write_setpoint(coating)

Design scope: moisture and coating to storage spec, caking risk down

Ships in: Granulex

agent.blend_bag

Blend-and-Bag

NPK blending, nutrient ratio, segregation, bagging and loading weight

Controls NPK blend ratio and anti-segregation moves to exact nutrient spec using Granvis nutrient sensing as feedback, and holds bagging and loading to exact weight and spec with every lot tied to its genealogy.

granvis.read_nutrientblend.predict_ratioplc.write_setpoint(blend)

Design scope: nutrient ratio and bag weight on spec, rework down

Ships in: Blendex

agent.defect_inspect

Defect-and-Inspect

Granule size and shape, dust, caking precursors, broken prills, bag defects, conveyor faults

Runs multi-camera granule vision at the plant edge for size and shape distribution, dust plumes, caking precursors, broken prills, bag defects and belt contamination, flags off-spec seconds to minutes ahead and attributes each fault to the granulator, dryer or coating state that caused it.

vision.stream(cams)fault.predictdefect.attribute

Design target: 50 to 120 ms p95 inference per frame at the edge

Ships in: Granvis

agent.quality_nutrient

Quality-and-Nutrient

Nutrient content, moisture, granule strength, emissions sensing, product quality

Fuses online nutrient and moisture analyzers with granule vision and CO2, NOx and ammonia-slip emissions sensing into one control-grade quality signal, predicts off-spec and emissions excursions before they happen and proposes the recipe and process moves that protect spec and permit margin.

analyzer.read_nutrientemissions.predictspec.check

Design scope: quality and emissions predicted ahead, not assayed behind

Ships in: Granvis

agent.yield_takt

Yield-and-Takt

Yield, off-spec and recycle, energy, emissions, line balancing, changeovers

Prices every candidate move in tonnes on spec, gigajoules per tonne and kilograms of CO2, NOx and ammonia slip, sequences grade changeovers and recycle balancing, and keeps synthesis, granulation and bagging paced so no unit starves the next.

cuopt.sequenceenergy.budgetemissions.budget

Design scope: yield up, energy, emissions and off-spec down

Ships in: Nitrotwin

agent.robot_handling

Robot-and-Handling

Bag palletizing, bulk loading, materials handling, inspection rovers

Drives bag palletizing, bulk loading and materials handling, and inspection rovers in high-dust or high-ammonia areas, with perception and motion policies validated in simulation first, inside safety zones, with audited actions and operator approval. It does not claim plant-wide robotic labor.

isaac.policy(palletize)robot.move(bounded)zone.check

Design scope: constrained handling, safety zones, approvals

Ships in: Blendex

agent.quality_conf

Quality-and-Conformance

Right-first-time, non-conformance, lot genealogy, traceability

Builds the lot genealogy: conversion and energy per tonne, melt concentration, granule distribution and moisture, nutrient assay, emissions readings, every setpoint move and every human decision, and gates release against product spec and the plant's quality and emissions procedures.

mes.release_lotgenealogy.writeaudit.write

Design scope: complete, immutable release records

Ships in: Complex tier

agent.fert_knowledge

Fertilizer-Knowledge

Grounded process, safety and emissions questions

Answers process engineers', operators' and HSE leads' questions over product and process specs, safety and emissions procedures, standards, recipes and lot genealogy, with a citation on every answer. It has no write tools and cannot act on the plant.

rag.retrieve(cited)answer.compose

Design rule: every answer cites a source; no write tools

Ships in: Every tier

agent.orchestrator · coordinates all eleven

Complex Orchestrator

Planning, arbitration, safety gating, human approval, twin rehearsal

Plans the run, rehearses high-impact moves on the Nitrotwin, arbitrates between agents that want the same actuator, enforces the autonomy stage per loop and routes anything above the site threshold, and every ammonia-loop move outside the bounded envelope, to a named human. Grounds its reasoning in the plant's specs, safety and emissions procedures through cited retrieval.

plan.composepolicy.evaluateapproval.requesttwin.simulate

Design rule: every write policy-checked, every output cited

Ships in: Every tier

Design targets

What the platform is engineered against

The numbers Nitreum is engineered against, from the GPU utilization plan.

50–120 ms p95 edge inference for granule size, shape, dust, caking and bag-defect frames
8–40 cameras per synthesis, granulation or bagging unit, 1080p or 4K at 15 to 30 FPS
1–10 Hz sensor fusion of vision, analyzer, historian, emissions, acoustic and thermal streams
2–5 model families fine-tuned per design-partner cohort
500–2,000 GPU-hours of fine-tuning per design-partner cohort
50k–250k synthetic rare-upset images and scenarios per cohort, labeled as synthetic

Design targets from the GPU utilization plan, all marked aspirational in the architecture. Nothing on this page is a measured plant result; measurements start when the first design-partner unit runs in shadow mode.

Developers

Every action is a record

There is no SDK to download yet. What design partners get is the integration surface: connectors, an autonomy policy declared per loop, and an audit record for every reading, recommendation, write and approval. This is the shape of one record, illustrative.

What the surface gives you

  • Connectors to DCS, APC, historian, granulation control, analyzers, emissions sensors, lab, MES, cameras and meters, with declared allow-lists and limits
  • An autonomy policy per loop: stage, tags, rate and magnitude limits, safety envelope, named approvers
  • Citations on every recommendation to the spec, procedure or permit it relied on
  • Model versions named in every record, with rollback by version
  • Export of the audit log and lot genealogy to your quality and HSE systems

What the docs cover Developer overview

audit record · illustrative
// one write, as the audit log would hold it
{
  "run": "run_scn_01",
  "step": "granulate.control",
  "agent": "agent.granulate",
  "stage": "bounded",
  "action": { "tool": "dcs.write_setpoint", "tag": "GRAN1.RECYCLE_RATIO" },
  "limits": { "max_step": "declared per tag", "per": "declared per tag" },
  "evidence": ["granvis.read_distribution", "twin.validate"],
  "citation": "spec:UREA-46 granule v3 §2",
  "safety": "SIS envelope read-only · inside",
  "policy": "permitted",
  "models": { "size_moisture": "versioned", "policy": "versioned" },
  "human": null,
  "outcome": "distribution inside band · recycle trimmed"
}
From the control room

Who this is built for

The three people in a fertilizer complex whose week changes when the process runs itself, and what each of them needs from Nitreum.

Economic buyer

Complex or Plant Operations Manager

Owns production rate, quality, yield and off-spec, energy, emissions and safety. Wants autonomous, higher-yield, lower-energy, lower-emissions production and a number that justifies the spend.

Champion

Process or Production Engineer

Owns synthesis, evaporation, granulation and blending recipes and process windows, energy and yield. Approves and corrects the agents in assist mode; those corrections train the models.

Approver

Sustainability, HSE and Energy Lead

Owns energy, CO2, NOx and ammonia-slip emissions, process safety, environmental compliance and the license to operate. Needs every action grounded, cited and written to an immutable record.

IT/OT and process safety approve the deployment; safety is a gating stakeholder for ammonia. There are no customer quotes on this site yet; design partners will speak for themselves when they choose to.

Integrations

It speaks plant, not cloud

Nitreum reads and writes through the systems already in the control room. No parallel historian, no new HMI, no rip-and-replace. Connectors are built against each design partner's stack first; long-tail integrations are out of scope for the first release.

DCS, APC and historian

Reformer, ammonia loop, reactor and evaporator control and the plant historian

Setpoint reads, guarded writes, safety systems untouched

Granulation and prilling control

Granulator, prill tower, dryer, cooler and coating drum controls

Recycle, spray, temperature and coating setpoints inside windows

Online analyzers

Nutrient, moisture and concentration analyzers, NIR and granule analyzers

Continuous quality state, fused at the edge

Emissions sensing

CO2, NOx and ammonia-slip sensors and permit records

Read and verified; excursions predicted, limits never optimized against

Blending and bagging

NPK blender, dosing gates, bagging and loading lines

Ratio and weight setpoints inside approved windows

Cameras and robots

Fixed cameras on granule, belt and bagging stations; Isaac-driven palletizing and loading cells

Frames, defect events, bounded handling

Plant MES, LIMS and quality

Orders, grade specs, lab assays, lot genealogy

Targets in, release records out

Identity (planned)

SSO and role-based access; SOC 2 on the roadmap

Named approvers, scoped roles

See all integrations

Guardrails

An agent that can move a setpoint needs a leash

Nitreum writes to production equipment in a plant that handles ammonia. Every capability is scoped, every write is policy-checked, every output is cited, and every action is written to an append-only audit log the plant owns.

  • Bounded action space. Each agent can only write to an explicit tag allow-list, through approved DCS or APC interfaces, inside per-tag rate and magnitude limits, at the autonomy stage the plant has set.
  • Safety systems are read, never written. Safety-instrumented systems, interlocks, trip settings and emissions permit limits stay with the plant's process-safety program and the people who own it.
  • Policy engine before every write. Autonomy stage, safety envelope, interlock state, grade, shift and operator presence are evaluated before a setpoint moves. Any ammonia-loop move beyond the envelope waits for a named approver.
  • Grounded and cited. Every recommendation carries a citation to the spec, procedure or permit it relied on. Retrieval is tenant-isolated and permission-aware.
  • Immutable audit log. Append-only, exportable and retained on the plant's own storage, aligned to the plant's quality, emissions and process-safety record-keeping.
  • Hard fallback. If the edge node, the network or a model stops, the plant keeps running on its existing DCS, APC and safety systems.
  • Tenant and IP isolation. Recipes, process settings and plant IP never cross a customer boundary. On-prem and plant-edge deployment available.

Assurance posture

Assurance and certification status
ItemScopeStatus
SOC 2 Type I readinessCloud control plane QUEUED Roadmap, first 6 months
SOC 2 Type IICloud control plane QUEUED Roadmap, 6 to 12 months
Process-safety and emissions proceduresGrounding and record-keeping RUNNING Design basis for retrieval and the audit log
Per-tenant isolationData, memory, models RUNNING Design rule
On-prem and plant-edge deploymentIP- and safety-sensitive sites RUNNING Design option

Nitreum supports your process-safety, quality and emissions records. It is not a certification and it does not replace your safety program or management of change.

Read the security overview

Enterprise

Standardize autonomy across the group

One policy model, one audit trail and one set of yield, energy, emissions and granule-quality benchmarks across every complex in the group, with each site's recipes, process settings and emissions models kept private to that site.

Talk to us Enterprise details

  • Multi-site plant-edge fleet with shared model governance
  • Custom product, process and emissions models per site
  • SSO and role-based access, named approvers (roadmap, 6 to 12 months)
  • Model versioning, validation reports and rollback
  • On-prem or private-cloud deployment
  • SLAs and outcome-based components on the highest-value workflows
FAQ

Straight answers

The questions complex operations managers, process engineers and HSE leads ask in the first meeting.

Only at the autonomy stage your plant has set, and only to an explicit allow-list of low-risk loops inside documented limits, through the approved DCS or APC interfaces. Every design partner starts in shadow mode, where Nitreum predicts and writes nothing. Assist mode follows, where a process engineer approves each recommendation. Bounded autonomy on granulation, conditioning and blending loops comes after the safety and ROI gates agreed up front.

Get started

See the platform on your unit

One unit, one baseline, shadow mode first. We will show you the run record before anything is written.