Connectors
Declared read and write scopes for DCS, APC, historian, granulation control, analyzers, emissions sensors, lab, MES, cameras, bagging lines and meters.
There is no public SDK yet. What exists is the integration surface design partners work with: connectors, an autonomy policy per loop, cited recommendations, versioned models and an audit record for every action. This page describes that surface honestly.
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.
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.
// 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"
}
Declared read and write scopes for DCS, APC, historian, granulation control, analyzers, emissions sensors, lab, MES, cameras, bagging lines and meters.
Stage, tag allow-list, rate and magnitude limits, safety envelope and named approvers per loop, versioned like any other change.
Every recommendation names the spec, procedure or permit it relied on; retrieval is tenant-isolated and permission-aware.
The best or cheapest model serves each step; high-volume granule vision moves to fine-tuned open models, reasoning steps use frontier models.
Golden datasets and model-as-judge evaluations gate model and prompt changes in CI.
Audit log and lot genealogy export to the plant's quality and HSE systems.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Goal, plan, thought, action, observation, exactly as the orchestrator would record it.
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.
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.
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.
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.
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.
Execute plan #9 at the bounded stage: loop temperature, evaporator, granulator, coating and blend writes proceed; emissions are verified continuously; the purge move waits.
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.
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.
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.
| Stage | What the agent does | What the person does | When |
|---|---|---|---|
| Shadow | Predicts conversion, concentration, granule quality, nutrient content, energy, emissions and off-spec risk; writes nothing | Runs the plant as today; compares predictions to assay, historian and engineer outcomes | First phase with every design partner |
| Assist | Recommends bounded loop, evaporation, granulation, coating and blend moves with the evidence | A process engineer approves or rejects each one | After accuracy is proven against the baseline |
| Bounded | Writes low-risk granulation, conditioning and blending setpoints inside documented recipe, quality, safety, emissions, equipment and rollback limits | Approves anything above the limits and every ammonia-loop move beyond the envelope; reviews the shift record | After the safety and ROI gates agreed up front |
| Exceptions | Escalates anything outside its envelope, safety-adjacent moves and release decisions | Always decides these; the agent never does | Permanent |
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
Throughput, recycle balancing, energy and emissions allocation and grade-changeover sequencing under constraints, recomputed on the GPU when the complex is disrupted.
ETL over historian, quality, emissions and vision data for feature generation, quality correlation and cross-site benchmarks on the GPU.
Bag palletizing, bulk loading, materials handling and inspection rovers, with perception and motion policies built and validated in simulation before they move a pallet.
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.
Reformer, ammonia loop, reactor and evaporator control and the plant historian
Setpoint reads, guarded writes, safety systems untouched
Granulator, prill tower, dryer, cooler and coating drum controls
Recycle, spray, temperature and coating setpoints inside windows
Nutrient, moisture and concentration analyzers, NIR and granule analyzers
Continuous quality state, fused at the edge
CO2, NOx and ammonia-slip sensors and permit records
Read and verified; excursions predicted, limits never optimized against
NPK blender, dosing gates, bagging and loading lines
Ratio and weight setpoints inside approved windows
Fixed cameras on granule, belt and bagging stations; Isaac-driven palletizing and loading cells
Frames, defect events, bounded handling
Orders, grade specs, lab assays, lot genealogy
Targets in, release records out
SSO and role-based access; SOC 2 on the roadmap
Named approvers, scoped roles
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.
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I readiness | Cloud control plane | QUEUED Roadmap, first 6 months |
| SOC 2 Type II | Cloud control plane | QUEUED Roadmap, 6 to 12 months |
| Process-safety and emissions procedures | Grounding and record-keeping | RUNNING Design basis for retrieval and the audit log |
| Per-tenant isolation | Data, memory, models | RUNNING Design rule |
| On-prem and plant-edge deployment | IP- 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.
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.
Safety-instrumented systems, interlocks, trip settings and permit limits are not optimization variables. Nitreum reads and verifies them, writes them to an immutable audit log and never writes to them. Any ammonia-loop move outside the bounded envelope waits for a named process engineer and a process-safety approver, and management of change stays with your plant. Nitreum is grounded in your process-safety and emissions procedures; it is not a certification and does not replace them.
Nitreum sits above your existing automation as a supervisory layer. If it stops, the plant keeps running on its current DCS, APC and safety systems. A Nitreum outage degrades the plant to the way it runs today, not to a stop.
The first phase is shadow mode on one unit: Nitreum reads your historian, analyzers, emissions sensors, lab assays and MES while you run the plant as usual, and we measure its predictions against your assay, historian and engineer outcomes. Recommendations start when accuracy is proven against that baseline, and improve as site-specific history and engineer corrections accumulate.
Recipes, process settings, product and emissions models and plant IP are tenant-scoped and never used to train another customer's models. Retrieval is multi-tenant isolated and permission-aware. Cross-site learning, where a customer opts in, is federated and IP-isolated. On-prem and plant-edge deployment is available for sensitive sites.
You are, the same as with any control strategy. That is why every write is policy-checked, bounded, logged and reversible, every output carries a citation to the spec or procedure it relied on, and anything above your threshold waits for a named approver. The audit log records the request, the reasoning, the limits applied and the human decision.
As a design partner, on one unit, with one hard metric: energy per tonne on the ammonia loop, granule size distribution and moisture on a granulator, off-spec and recycle tonnes, or emissions variance. We instrument the unit in shadow mode, measure the baseline, move to assist mode when accuracy is proven, and expand only when the number holds.
Full multi-unit autonomy across the entire complex, long-tail integrations beyond the design partners' stacks, and self-serve onboarding. The first release is one wedge workflow, its connectors, the agent loop with human checkpoints, the review console and the assurance-grade quality, emissions and safety audit log.
Design partners get the integration surface and the people who built it. Tell us what you want to connect.
↑↓ navigate↵ openesc close