Developers

Autonomy policy is declared. Review it like code.

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, permit gating and an audit record for every action. This page describes that surface honestly.

ConnectorsPolicy per loopAudit records

run_scn_0418 · agent graph · scenario 10 nodes · 1 approval gate
01 · intake_screen Read influent and forecast ✓ SUCCEEDED 02 · orchestrator Rehearse the next 24 hours ✓ SUCCEEDED 03 · quality_anomaly Fuse cameras and analyzers ✓ SUCCEEDED 04 · dose_coagulate Compute the dose curve ✓ SUCCEEDED 05 · dose_coagulate Trim the coagulant setpoint ✓ SUCCEEDED 06 · aerate_bio Minimum-energy DO schedule ✓ SUCCEEDED 07 · orchestrator Blower move approved ◆ APPROVAL 08 · membrane_disinfect Flux hold and backwash timing ✓ SUCCEEDED 09 · compliance_energy Permit conformance check ✓ SUCCEEDED 10 · conformance Write the shift record ✓ SUCCEEDED

Illustrative scenario: one municipal activated-sludge wastewater plant with a membrane train, planning the next 24 hours after a rain forecast. Not a measured run.

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 SCADA, PLC and DCS, dosing, aeration and membrane controls, online analyzers, lab, utility MES, cameras and meters, with declared allow-lists and limits
  • An autonomy policy per loop: stage, tags, rate and magnitude limits, named approvers
  • Citations on every recommendation to the permit, SOP or regulation it relied on
  • Model versions named in every record, with rollback by version
  • Export of the audit log and shift record to your permit and quality systems

What the docs cover Developer overview

audit record · illustrative
// one write, as the audit log would hold it
{
  "run": "run_scn_0418",
  "step": "dose.write",
  "agent": "agent.dose_coagulate",
  "stage": "bounded",
  "action": { "tool": "plc.write_setpoint", "tag": "DOS1.SP" },
  "limits": { "max_step": "declared per tag", "per": "declared per tag" },
  "evidence": ["analyzer.read_influent", "vision.fuse_state"],
  "citation": "sop:DOSE-07 §3 · permit:NPDES-WWTP-A §II.A",
  "permit_check": "inside margin",
  "models": { "dose_response": "versioned", "policy": "versioned" },
  "human": null,
  "rollback": "38 mg/L",
  "outcome": "42 mg/L · inside declared window"
}
Capabilities

What the surface gives you

Connectors

Declared read and write scopes for SCADA, PLC and DCS, dosing, aeration and membrane controllers, analyzers, lab, utility MES, cameras and meters.

Autonomy policy

Stage, tag allow-list, rate and magnitude limits, permit set and named approvers per loop, versioned like any other change.

Cited recommendations

Every recommendation names the permit, SOP or regulation it relied on; retrieval is tenant-isolated and permission-aware.

Model router

The best or cheapest model serves each step; high-volume time-series and vision moves to fine-tuned open models, compliance and permit reasoning uses frontier models.

Evaluation gates

Golden datasets and model-as-judge evaluations gate model and prompt changes in CI.

Export

Audit log, shift record and drafted reports export to the plant's permit and quality systems.

Run timeline

What a run record contains

Every Hydrira run is an ordered, inspectable sequence. This is run_scn_0418, an illustrative scenario: one municipal activated-sludge wastewater plant with a membrane train, planning the next 24 hours after a rain forecast. Ten steps, nine automatic, one human approval on the blower setpoint move, every action written to the shift record.

run_scn_0418 scenario · not measured SUCCEEDED
  1. 01 Read influent and forecast SUCCEEDED 1.2 s

    Intake-and-Screen · Flow, turbidity, ammonia and alkalinity at the headworks, and a 24-hour rain forecast that raises the expected influent by mid-afternoon.

  2. 02 Rehearse the next 24 hours SUCCEEDED 4 min 10 s

    Plant orchestrator · Simflo evaluates candidate dose, DO and flux plans over the 24-hour horizon and keeps the plans that hold permit margin through the surge.

  3. 03 Fuse cameras and analyzers SUCCEEDED 180 ms

    Quality-and-Anomaly · Clarifier blanket, foam and colour from the basin cameras fused with turbidity, pH, nutrient and residual analyzers into one calibrated plant state.

  4. 04 Compute the dose curve SUCCEEDED 2.4 s

    Dose-and-Coagulate · Coagulant and polymer dose ramp for the surge window under turbidity, phosphorus, sludge and chemical-cost constraints, cited to the plant's dosing SOP.

  5. 05 Trim the coagulant setpoint SUCCEEDED 0.6 s

    Dose-and-Coagulate · A bounded setpoint move inside the declared rate and magnitude limits for the dosing pump, with the rollback value recorded first.

  6. 06 Minimum-energy DO schedule SUCCEEDED 3.1 s

    Aerate-and-Bio · Blower and DO setpoint schedule across the basins that meets the nitrogen and phosphorus targets at the lowest kilowatt-hours the biological state allows.

  7. 07 Blower move approved APPROVAL 6 min 02 s

    Plant orchestrator · The DO setpoint change is above the plant's threshold for this loop. The process engineer on shift reviews the predicted nutrient margin and approves.

  8. 08 Flux hold and backwash timing SUCCEEDED 1.8 s

    Membrane-and-Disinfect · Flux held through the surge and the next backwash moved earlier, inside the integrity envelope; the disinfection residual minimum is untouched.

  9. 09 Permit conformance check SUCCEEDED 0.9 s

    Compliance-and-Energy · Every planned setpoint checked against the discharge permit, the nutrient limits and the residual minimum, with excursion risk forecast for the horizon.

  10. 10 Write the shift record SUCCEEDED 0.3 s

    Quality-and-Conformance · Inputs, model versions, predictions, limits, the approval and every write appended to the immutable shift record the plant owns.

Tool calls

Streaming a run

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_0418
  1. 05:40:02scada.read_influent({ plant: "WWTP-A", tags: ["FLOW", "NTU", "NH4", "ALK"] })
  2. 05:40:03ok flow 412 L/s · turbidity 118 NTU · ammonia 31 mg/L · alkalinity 184 mg/L
  3. 05:40:03weather.read_forecast({ horizon_h: 24 })
  4. 05:40:04ok rain from 14:00 · expected influent +38% by 17:00
  5. 05:40:04twin.simulate({ horizon_h: 24, candidates: 240, objective: ["permit_margin", "kwh", "chemical"] })
  6. 05:44:14ok 240 plans evaluated · 31 hold permit margin through the surge · best plan selected
  7. 05:44:15vision.fuse_state({ cameras: ["CLAR-1", "CLAR-2", "AER-3"], analyzers: "all" })
  8. 05:44:15ok blanket 1.1 m · foam none · effluent turbidity 1.8 NTU · residual 0.9 mg/L
  9. 05:44:16cuopt.solve_dose({ window_h: 12, constraints: ["NTU", "P", "sludge", "cost"] })
  10. 05:44:18ok coagulant ramp 38 → 46 mg/L from 13:30 · polymer unchanged · cite sop:DOSE-07 §3
  11. 05:44:19policy.evaluate({ loop: "dose", stage: "bounded", tag: "DOS1.SP" })
  12. 05:44:19ok permitted · max_step 4 mg/L per 15 min · rollback 38 mg/L
  13. 05:44:19plc.write_setpoint({ tag: "DOS1.SP", value: 42, unit: "mg/L" })
  14. 05:44:20ok written · ack from PLC · audit id 0418-05
  15. 05:44:20cuopt.solve_blowers({ basins: 4, constraints: ["NH4", "NO3", "P", "DO_min"] })
  16. 05:44:23ok DO 2.0 → 1.6 mg/L basins 1–3 from 06:00 · predicted −9% kWh · nutrient margin held
  17. 05:44:24policy.evaluate({ loop: "aeration", stage: "assist", tag: "BLW.DO_SP" })
  18. 05:44:24above threshold for this loop · routed to approve.human · engineer on shift notified
  19. 05:50:26approved by the process engineer on shift · reason: nutrient margin 0.6 mg/L above limit
  20. 05:50:27membrane.schedule_backwash({ train: "MBR-2", surge_at: "14:00" })
  21. 05:50:29ok flux held 24 LMH · backwash moved 16:00 → 13:15 · residual minimum untouched
  22. 05:50:29permit.evaluate({ permit: "NPDES-WWTP-A", horizon_h: 24 })
  23. 05:50:30ok all parameters inside limit · excursion risk 24 h: low · cite permit §II.A
  24. 05:50:30audit.commit({ run: "run_scn_0418", steps: 10, approvals: 1 })
  25. 05:50:30ok shift record written · immutable · exportable

Reasoning trace

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

GoalHold effluent turbidity, nutrients and disinfection residual i…

Hold effluent turbidity, nutrients and disinfection residual inside the discharge permit for the next 24 hours while taking aeration energy and coagulant use to the minimum the permit margin allows.

PlanRead influent and the forecast; rehearse the horizon on Simflo…

Read influent and the forecast; rehearse the horizon on Simflo; fuse the plant state; compute dose and DO schedules; write the dose inside bounds; route the DO move for approval; hold flux and move the backwash; check the permit; commit the record.

ThoughtRain arrives mid-afternoon and the influent will rise by about…

Rain arrives mid-afternoon and the influent will rise by about a third. Dosing has to ramp before the surge, not after, and the DO schedule has to keep nutrient margin through it.

Actioncuopt.solve_dose over a 12-hour window under turbidity, phosph…

cuopt.solve_dose over a 12-hour window under turbidity, phosphorus, sludge and cost constraints; plc.write_setpoint on the coagulant pump inside the declared rate and magnitude limits.

ObservationThe dose ramp holds predicted effluent turbidity under 2 NTU t…

The dose ramp holds predicted effluent turbidity under 2 NTU through the surge. The DO schedule saves energy but is above the threshold set for the aeration loop.

ThoughtEnergy never outranks permit margin. The DO change goes to the…

Energy never outranks permit margin. The DO change goes to the engineer with the predicted nutrient margin attached, and nothing is written until it is approved.

Actionapprove.request to the process engineer on shift; membrane.sch…

approve.request to the process engineer on shift; membrane.schedule_backwash to hold flux and move the next backwash ahead of the surge; permit.evaluate across the horizon.

OutcomeTen steps, one human approval, all parameters inside limit on …

Ten steps, one human approval, all parameters inside limit on the forecast, and the shift record written. Illustrative scenario; nothing here is a measured plant result.

Workflow

From idea to a plant, safely

  1. Declare. Tools, tags and limits for the agent, the permit set to check against, and the autonomy stage for the loop.
  2. Shadow. Run against live plant data; compare predictions to lab, analyzer and SCADA outcomes; nothing is written.
  3. Evaluate. Golden datasets and model-as-judge checks in CI before a model or prompt version is promoted.
  4. Rehearse. High-impact moves are simulated on Simflo where a twin exists for the process.
  5. Assist, then bounded. Writes only after the accuracy gate and compliance sign-off, inside declared limits, with Permia checking every one.
  6. Record and retrain. Every action and correction is logged; corrections become training events.
Autonomy

Four stages, set per loop

A plant does not go from manual to bounded control in one step. Hydrira makes the stage explicit per loop, auditable and reversible at any time, and some decisions never leave the person.

Autonomy stages and the human role at each
StageWhat the agent doesWhat the person doesWhen
ShadowPredicts water quality, fouling, excursion risk and energy; writes nothingRuns the plant as today; compares predictions to lab, analyzer and SCADA outcomesFirst phase with every design partner
AssistRecommends dose, DO, flux and cleaning moves with predicted quality, energy and permit impactApproves, corrects or rejects each move; corrections train the modelsAfter accuracy is proven against the plant's own baseline
BoundedWrites to an allow-list of low-risk loops inside declared rate and magnitude limitsSets the limits, watches the record, pulls the loop back at any timePer loop, after the assist-mode gate and compliance sign-off
ExceptionsEscalates anything above the threshold, every permit-adjacent move and every releaseDecides; the operator of record is never removed from compliance decisionsAlways
Multi-agent handoff

Agents negotiate, they do not collide

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

Dose-and-Coagulate and Aerate-and-Bio both want phosphorus

  1. 01Conflict detected SUCCEEDED0.2 s

    Chemical phosphorus removal (more coagulant) and biological phosphorus removal (more aeration) both reach the target; each agent proposes its own route.

  2. 02Orchestrator arbitrates SUCCEEDED1.4 s

    Simflo scores both routes on permit margin, kilowatt-hours and chemical cost over the horizon; the permit margin is identical, so cost decides.

  3. 03Plan handed back SUCCEEDED0.3 s

    The biological route wins for this shift; the dosing agent holds coagulant at the clarity dose and the aeration agent takes the phosphorus target.

  4. 04Both requests logged SUCCEEDED0.1 s

    Both proposals, the arbitration and the chosen route are written to the shift record so a process engineer can see why.

Arbitration rules

  • Permit margin outranks everything. No arbitration may thin a permit margin, a disinfection residual minimum or an integrity limit, whatever it saves.
  • Health and safety outrank cost. Where a route touches disinfection or pathogen removal, the conservative route wins by rule.
  • The orchestrator decides, the agents do not negotiate directly. An agent never writes to another agent's actuator.
  • Arbitration is a step. It is typed, timed and logged like any other, and it is reversible.

See the agent roster

Accelerated computing

Physical AI, at the plant edge

A treatment plant runs around the clock on variable influent, and many utilities keep plant data on site, so perception and control inference run at the plant edge. Hydrira 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 · TensorRT · DeepStream · Holoscan

Plant-edge inference

TensorRT-optimized time-series and vision models at the plant edge; DeepStream pipelines for clarifier, basin and filter cameras; Holoscan fusing camera streams with turbidity, pH, chlorine and nutrient analyzers at 1 to 10 Hz. Jetson Thor is planned.

Triton · NIM · NVIDIA AI Enterprise

Model serving

Water-quality forecasting, anomaly detection, control recommendation and compliance retrieval served with per-tenant routing, model versioning and an audit id on every call. Self-hosted for utility on-prem and edge deployment. Planned.

DGX / HGX · NeMo

Training and fine-tuning

Time-series transformers, vision models and NeMo-tuned process and compliance reasoning trained on plant telemetry, operator corrections, images, alarms, lab results, permits and SOPs. Design target: weekly fine-tuning per design-partner cohort, then monthly fleet refreshes. Planned.

Omniverse · OVX · Modulus

The as-run twin

Simflo runs plant hydraulics, clarifier and filtration behaviour, membrane fouling, oxygen transfer and biological response as a GPU simulation calibrated to the live plant, with Modulus surrogates for fast evaluation. Planned.

Cosmos · Omniverse Replicator

Synthetic rare events

Wet-weather surges, sensor drift, foaming, fouling, filtration breakthrough and biological upsets generated as scenario variants to stress-test autonomy and train the perception and control agents. Planned.

cuOpt

Optimization

Blower and pump scheduling, chemical dosing windows, membrane cleaning, backwash timing and fleet maintenance routes solved under energy tariff, labour, asset and permit constraints.

RAPIDS

GPU analytics

ETL over high-volume SCADA tags, lab results, membrane data, alarms and image metadata to build features and golden evaluation sets. Planned.

Isaac · Jetson

Robotics

Supervised robotic sampling routes, asset-inspection rovers and materials handling across intake, treatment and disinfection, where plant policy allows robots. Planned.

Integrations

It speaks plant, not cloud

Hydrira reads and writes through the systems already in the plant. 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.

SCADA and historians

Plant SCADA, historians, PLC and DCS interfaces

Tag reads at 1 to 10 Hz, guarded setpoint writes, interlocks untouched

Dosing and chemical skids

Coagulant, polymer, pH-adjust and disinfectant dosing controllers

Dose reads, bounded setpoint writes inside declared limits

Aeration and blowers

Blower controls, DO and ammonia-based aeration control

DO and blower reads, bounded setpoint writes after approval

Membrane skids

Membrane and RO skid PLCs, TMP, flux, conductivity, integrity monitors

Reads; flux and backwash writes inside the integrity envelope

Online analyzers

Turbidity, pH, chlorine residual, nutrient, TOC and flow analyzers

Reads; drift and fault flags

Lab and LIMS

Lab information systems, jar-test and grab-sample records

Reads for labels and calibration

Cameras and robots

Fixed cameras on clarifiers, basins, filters and membrane rooms; inspection robots

Streams fused at the edge; supervised routes

Utility MES, CMMS, permits

Utility MES, maintenance systems, permit and reporting systems, weather

Reads; shift record and report drafts written back

See all integrations

Guardrails

An agent that can move a setpoint needs a leash

Hydrira writes to control equipment in a plant that keeps a community's water safe. 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, inside per-tag rate and magnitude limits, at the autonomy stage the plant has set.
  • Permit limits are read, never written. Permit-limit setpoints, disinfection residual minimums, integrity limits and discharge release decisions stay with the permit and the operator of record.
  • Policy engine before every write. Autonomy stage, interlock state, permit margin, excursion forecast and operator presence are evaluated before a setpoint moves.
  • Grounded and cited. Every recommendation carries a citation to the permit, SOP or regulation 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 Safe Drinking Water Act, discharge-permit and EU Water Framework record-keeping.
  • Hard fallback. If the edge node, the network or a model stops, the plant keeps running on its existing SCADA, PLC and DCS control and interlocks.
  • Tenant isolation and critical-infrastructure posture. Telemetry, permits, SOPs and models never cross a customer boundary. On-prem and edge-only deployment available for utilities.

Assurance posture

Assurance and certification status
ItemScopeStatus
SOC 2 Type I + critical-infrastructure cyber reviewCloud control plane, edge QUEUED Roadmap, first 6 months
SOC 2 Type IICloud control plane QUEUED Roadmap, 6 to 12 months
SDWA · discharge permits · EU WFD · nutrient and PFAS rulesGrounding and record-keeping RUNNING Design basis for retrieval and the audit log
Per-tenant isolationData, memory, models RUNNING Design rule
On-prem or edge-only deploymentUtilities, critical infrastructure RUNNING Design option

Hydrira supports your compliance records. It is not a certification, it does not replace your permit and it never removes the operator of record from a compliance decision.

Read the security overview

FAQ

Straight answers

The questions operations managers, process engineers and compliance 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. Every design partner starts in shadow mode, where Hydrira predicts and writes nothing. Assist mode follows, where a process engineer approves each move. Bounded write-back comes last, per loop, after the accuracy gate and compliance sign-off, and can be pulled back at any time.

Get started

Build on the run engine

Design partners get the integration surface and the people who built it. Tell us what you want to connect.