The orchestrator plans, the agents act
A run starts as a goal, becomes a plan, and executes as a graph of typed steps. The active path is always visible, always logged, always reversible.
RUNNING APPROVAL SUCCEEDED
Physical AI · Rolling-stock manufacturing autonomy
The plant runs on takt. You decide how far it runs itself.
Railira is an agent operating system for rail rolling-stock plants. Specialist agents control EN 15085 carbody welding and geometry, bogie and running-gear assembly, livery and protective coatings, fit-out and carbody-to-bogie marriage, and sequence the line, watched by fused inspection, rehearsed on an as-built train-and-plant twin, and bounded by a policy engine you control.
Illustrative scenario: Car 07 of a 4-car metro consist · shell line B · bogie shop · booth 2 · marriage station, one car, one approval gate
Design partners wanted · 2 to 4 plants · processes we are looking for
Carbody shell lines
Bogie and running-gear shops
Coating and livery booths
Final assembly and marriage
Fit-out and systems integration
Commissioning and test cells
Pre-launch. No customers, pilots or logos are claimed. The first cohort gets a paid pilot on one process against a baseline agreed in writing.
Run timeline · scenario
One scenario run, step by step
Every Railira run is an ordered, inspectable sequence. This is run_9b4e27: Car 07 of a 4-car metro consist · shell line B · bogie shop · booth 2 · marriage station. Scenario completes in 10 steps with one approval gate. Shell geometry held inside tolerance after a twin-ranked weld sequence, one heat-input change approved by the shift weld engineer, two torque traces routed to rework before brake test, the livery cure window protected in the sequence, marriage interface inside tolerance, car released with full genealogy.
run_9b4e27
car 07 · 4-car metro consist
illustrative scenario
SUCCEEDED
-
01
ingest.order
SUCCEEDED
0.8 s
Plant Orchestrator · Pulled the work packages for car 07 from MES and PLM: aluminium extrusion shell, EN 15085 weld class per joint, control-plan geometry tolerances, bogie torque specifications, livery recipe and cure window, fit-out and marriage sequence. Locked the approved control-plan envelope for the shift.
-
02
takt.sequence
SUCCEEDED
41 s
Line-and-Logistics · Sequenced the shift against live readiness: booth 2 cure window, bogie B-14 readiness, brake-test slot at 13:40, AMR fleet state and kit inventory. The plan moves car 07 marriage behind car 06 to keep the cure window and the test slot.
-
03
twin.simulate
SUCCEEDED
58 s
Train Twin · Simulated 18 candidate weld sequences for the roof-to-sidewall joints on the as-built twin and ranked them on predicted distortion, door-aperture geometry and heat input. Sequence #6 keeps the aperture inside tolerance with 2% less heat input than the standing sequence.
-
04
weld.sequence
SUCCEEDED
3 m 12 s
Weld-and-Structure · Recommended sequence #6 and the matching clamping plan to the shell line. Seam vision and laser-tracker geometry confirmed the roof-to-sidewall joints inside the control-plan tolerance on the first four seams.
-
05
approve.human
APPROVAL
52 s
Plant Orchestrator · Sequence #6 lowers heat input on the roof joints 2% below the standing weld procedure. Heat-input changes stay with a named engineer, so the step was held for the shift weld engineer and approved at 06:12:44 with the twin evidence attached.
-
06
bogie.torque
SUCCEEDED
continuous
Bogie-and-Running-Gear · Press-fit curves and torque traces on bogie B-14 read at the station. Two traction-motor mounting traces fell outside the expected profile and were routed to rework before brake test; the remaining safety-critical joints verified to spec.
-
07
coat.cure
SUCCEEDED
continuous
Coat-and-Livery · Booth 2 humidity and temperature, film thickness and flash time watched through the livery pass. One masking misalignment on the door band flagged by booth vision before the second coat; the cure window held and handed to the sequence as a hard constraint.
-
08
marry.align
SUCCEEDED
2 m 05 s
Marry-and-Couple · Carbody and bogie scans compared against target interface geometry before the lift. Fit-out readiness confirmed by Fitout-and-Interior for doors and glazing. Marriage guided inside tolerance; coupler and gangway checks verified and written to the twin.
-
09
inspect.fuse
SUCCEEDED
continuous
Quality-and-Anomaly · Weld and coating vision, in-line metrology, torque, wiring continuity and brake-test results fused at the edge across the car. Every finding localised to station, work package and shift, with the two torque reworks and the masking flag already closed.
-
10
car.release
SUCCEEDED
1 m 30 s
Conformance · Car 07 released: genealogy written (weld records per joint, geometry scans, torque traces, coating recipe and cure record, fit-out checks, marriage interface, approvals, test results) and dispositioned against the control plan and IRIS / ISO/TS 22163 criteria with cited evidence for the quality engineer'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.
- 05:58:02mes.read_workpackages({ car: "07", consist: "M4-118", shift: "A" })
- 05:58:03ok 142 work packages · control plan locked · EN 15085 classes mapped
- 05:58:04cuopt.sequence({ shift: "A", constraints: ["cure_window", "test_slot", "bogie_ready"] })
- 05:58:45ok plan released · car 07 marriage after car 06 · test slot 13:40 held
- 05:58:46twin.simulate({ joints: "roof-sidewall", candidates: 18 })
- 05:59:44ok best sequence #6 · aperture dev 0.6 mm · heat input −2%
- 05:59:45policy.evaluate({ sequence: 6, autonomy: "L2+" })
- 05:59:45ok 6 recommendations permitted · heat_input requires human approval
- 05:59:46weld.set_sequence({ line: "B", seq: 6, clamping: "plan-6" })
- 06:02:58ok 4 seams inside tolerance · tracker dev 0.5 mm
- 06:02:59approval.request({ action: "heat_input", delta: "-2%", joints: "roof" })
- 06:12:44ok approved by shift weld engineer · twin evidence attached · logged
- 06:12:45torque.read_trace({ bogie: "B-14", joints: "all" })
- 07:40:12trace out of profile · traction-motor mount M3, M4 · bogie B-14
- 07:40:13rework.route({ bogie: "B-14", joints: ["M3", "M4"], before: "brake_test" })
- 07:40:13ok routed · brake test slot held
- 08:05:00cure.window({ booth: 2, recipe: "livery-M4" })
- 08:31:20masking misalignment · door band · booth 2 · before coat 2
- 08:31:21ok masking corrected · cure window held · constraint sent to sequence
- 11:10:02scan.compare({ car: "07", bogie: "B-14" })
- 11:12:07ok interface inside tolerance · fit-out ready · marriage guided
- 11:12:08sensors.fuse({ car: "07", streams: ["vision", "metrology", "torque", "wiring"] })
- 13:58:40genealogy.write({ car: "07", packets: "full" })
- 14:00:10ok scenario complete · 10 steps · car 07 released
Reasoning trace
Plan, thought, action, observation, exactly as the orchestrator would record it.
GoalBuild car 07 through shell welding, bogie assembly, livery, fi…
Build car 07 through shell welding, bogie assembly, livery, fit-out and marriage on the shift plan, inside the control plan, with every safety-critical joint to spec and the cure window protected.
PlanSequence the shift first, so the cure window and the brake-tes…
Sequence the shift first, so the cure window and the brake-test slot are protected. Simulate the roof-to-sidewall weld sequence on the twin before the first seam. Read every torque trace at the station. Fuse inspection continuously. Hold any heat-input change for a human.
ThoughtThe standing weld procedure runs the roof joints hot enough to…
The standing weld procedure runs the roof joints hot enough to guarantee penetration on a cold fixture. With the clamping plan from the twin the same penetration holds at 2% less heat input and the door aperture stays inside tolerance, because the distortion is sequenced out rather than reworked out.
Actiontwin.simulate(candidates=18) returns sequence #6: roof joints …
twin.simulate(candidates=18) returns sequence #6: roof joints re-ordered, clamping plan 6, heat input down 2% on the roof joints.
ObservationSequence #6 predicts door-aperture deviation 0.6 mm against a …
Sequence #6 predicts door-aperture deviation 0.6 mm against a 1.5 mm tolerance. Three candidates scored lower on heat input but pushed predicted sidewall distortion past the limit and were discarded.
ActionRecommend sequence #6 to the shell line; six recommendations p…
Recommend sequence #6 to the shell line; six recommendations permitted; the heat-input change routed to the shift weld engineer with the twin evidence.
ObservationTwo traction-motor mounting traces on bogie B-14 fell outside …
Two traction-motor mounting traces on bogie B-14 fell outside the expected profile at 07:40:12. Routed to rework before brake test; the slot held. One masking misalignment on the door band flagged in booth 2 before the second coat.
OutcomeScenario complete. Shell inside tolerance, bogie joints to spe…
Scenario complete. Shell inside tolerance, bogie joints to spec after rework, livery inside the cure window, marriage interface inside tolerance. Car 07 released with full genealogy.
How it works
A goal becomes a plan becomes a run
Nothing about a Railira run is implicit. The goal is declared, the shift is sequenced, the weld sequence is simulated on the twin, each step is typed and bounded, and the outcome is written to the car's genealogy.
Autonomy is a dial, not a switch
L1 shadow, L2 assist, L3 bounded autonomy on low-risk actions, L4 supervised weld-parameter adaptation inside pre-approved control-plan envelopes. Each plant sets the level per agent, per tool, per shift, and every write above the threshold waits for a named approver. The four figures above are design targets, not measured results.
Agent roster
Ten agents, a twin and an orchestrator
Each agent owns a step of the plant, a bounded tool set and a metric the plant already measures. They negotiate for shared stations and sequence slots through the orchestrator, never directly. Five named products ship them.
Weld-and-Structure
EN 15085 carbody welding, large-structure joining, shell geometry
Fuses robotic weld parameters, seam vision, thermal signatures, fixture data, laser trackers and point clouds into one live estimate of weld quality and shell geometry. Predicts weld defects and geometry drift as the shell is built and recommends weld sequence, clamping, rework priority and inspection coverage inside the approved control-plan envelope. Heat-input and weld-sequence changes wait for a named engineer.
weld.read_paramsseam.visionweld.set_sequence
Bogie-and-Running-Gear
Wheelset press-fit, suspension, traction mounting, brakes, torque-to-spec
Reads wheelset press-fit curves, torque traces on safety-critical joints, bearing and motor or gearbox mounting telemetry, brake-system checks and station vision. Detects assembly anomalies, predicts ride and brake risk, and guides technicians through torque, shim, suspension and mounting decisions inside approved work instructions.
pressfit.read_curvetorque.read_tracestation.vision
Underframe-and-Propulsion
Traction equipment, HVAC, pantograph or third rail, batteries, cabling, continuity
Tracks traction equipment, HVAC, pantograph or third-rail gear, battery and cabling installation on the underframe, and predicts harness-routing and continuity risk from installation telemetry and wiring-tester results before commissioning finds it.
wiring.read_continuityinstall.read_statusrisk.predict
Coat-and-Livery
Surface prep, primer, livery, film build, anti-graffiti and anti-corrosion coats, flash, cure
Fuses booth cameras, surface-prep data, thickness gauges, flash and cure telemetry, humidity and temperature and recipe history. Predicts runs, dirt, adhesion risk, colour or livery mismatch, corrosion-protection gaps and cure-window conflicts before they reach acceptance, and hands flash and cure constraints to the line agent.
booth.visionthickness.readcure.window
Marry-and-Couple
Carbody-to-bogie marriage, couplers, gangways, consist assembly
Reconciles carbody and bogie scans against target geometry before the marriage, guides lift and alignment, verifies coupler and gangway installation, and records the as-built interface in the train twin.
scan.comparemarriage.guidecoupler.verify
Fitout-and-Interior
Seats, panels, doors, glazing, flooring, ADA/PRM interiors, cab fit-out
Validates interior fit-out against the work package: seats, panels, flooring, doors, glazing, cab equipment and accessibility requirements, from station vision and CAD-to-as-built matching, and flags fit and sequence risk before the car moves on.
station.visioncad.match_asbuiltfit.predict
Quality-and-Anomaly
Weld, geometry, coating, torque, wiring, brake and signaling defects
Fuses weld and coating vision, in-line metrology, torque, wiring, brake-test and signaling data into one estimate of build quality per car, localises every finding to a station, work package and shift, and couples it back to the process state that caused it.
sensors.fusemetrology.readtest.read_result
Line-and-Logistics
Line sequencing, JIS feeding, AMR and AGV flow, test and commissioning slots, takt
Sequences variant-rich production with cuOpt against live readiness: coating cure windows, bogie readiness, interior fit, rework risk, AMR and AGV state, inventory and test-cell availability. Feeds kits just in sequence, manages buffers and schedules brake, traction, signaling, ride-quality and haul tests.
cuopt.sequenceamr.dispatchtest.schedule
Robot-and-Inspect
Robotic weld, coating and assembly cells, AMR and AGV flow, inspection cameras
Supervises the robotic weld, coating and assembly cells and the AMR and AGV fleet: cell health, path variants validated in simulation before release, inspection-camera placement and coverage. Robot parameter changes stay inside approved bounds and approved paths.
isaac.validate_pathcell.read_healthcamera.coverage
Conformance
IRIS / ISO/TS 22163, TSI, AAR, APTA evidence, PPAP genealogy, release
Builds the genealogy record per car and work package, dispositions against the control plan and the standards the plant works to with cited evidence, and assembles the packets a quality engineer signs for acceptance. It blocks any action that has no evidence behind it.
genealogy.writedisposition.writeaudit.write
Train Twin
As-built train-and-plant simulation
Hosts the Omniverse as-built train-and-plant twin. Consumes shell geometry from Carbra, running-gear data from Bogira and coating state from Coatyx, simulates weld distortion, geometry build-up, coating coverage, marriage fit, commissioning readiness and line flow, and ranks candidate weld sequences, geometry strategies and build orders before the shift.
twin.simulatetwin.compare_asbuiltplan.rank
Plant Orchestrator
Planning, arbitration, human approval
Plans the shift, arbitrates between agents competing for the same station or sequence slot, enforces the autonomy level and routes anything above the risk threshold, weld heat-input and sequence changes first among them, to a named approver.
plan.composepolicy.evaluateapproval.request
Where it pays
Four loops, four metrics
Railira is not a dashboard. Each agent closes a loop a plant already measures in rework, repaint, torque escapes and line stoppage minutes. The tables show what each loop watches and what it is allowed to move.
Weld and geometry
Sequence the distortion out before the first seam
Weld parameters, seam vision, thermal signatures, fixture state and laser-tracker geometry are fused at the edge into one live estimate of weld quality and shell geometry. Carbra ranks weld sequences and clamping plans on the twin, recommends the one that holds the door aperture, and leaves heat-input changes to a named engineer.
- Weld defects and geometry drift predicted while the shell is built, not found at fit-out
- EN 15085 weld classes enforced per joint at call time
- Every joint labelled with its downstream geometry and acceptance outcome
agent.weld_structure SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Weld quality | Seam cameras, weld current, thermal | Weld sequence and clamping recommendations |
| Shell geometry | Laser trackers, point clouds | Rework priority, inspection coverage |
| Heat input | Weld parameters per joint | Under engineer approval only |
Bogie and torque
Catch the torque escape before brake test
Press-fit curves, torque traces, bearing and mounting telemetry and station vision are read as the bogie is built. Bogira detects the trace that is out of profile, routes the joint to rework before the brake test and keeps the slot.
- Press-fit and torque anomalies detected per joint, not sampled
- Missing parts, orientation and harness routing checked by vision
- Ride and brake risk predicted from build data
agent.bogie_gear SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Press-fit | Curve per wheelset | Station hold, rework routing |
| Torque | Trace per safety-critical joint | Rework before brake test |
| Completeness | Station vision | Missing-part and routing flags |
Livery and cure
Protect the cure window in the sequence
Booth cameras, film thickness, humidity, temperature and flash time are watched through every pass. Coatyx flags dirt, runs, masking errors and colour breaks before the next coat, and hands the cure window to Taktos as a constraint the sequence cannot break.
- Coating defects found before the next coat, not at acceptance
- Film build and cure predicted from recipe and environment
- Cure windows carried into the line plan
agent.coat_livery SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Surface and film | Booth cameras, thickness gauges | Inspection and rework routing |
| Environment | Humidity, temperature, flash time | Recipe inside the approved spec |
| Cure window | Cure telemetry | Constraint to Line-and-Logistics |
Marriage and takt
Marry on the first lift, on the planned slot
Carbody and bogie scans are compared against the target interface before the lift, fit-out readiness is confirmed, and the marriage is guided inside tolerance. Taktos has already sequenced the car so the bogie, the cure and the test slot line up.
- Interface geometry checked before the lift, not after
- Fit-out, coupler and gangway readiness confirmed in the same record
- Sequence built on live readiness, not static routings
agent.marry_couple SUCCEEDED
| Signal | Watches | Moves |
|---|---|---|
| Interface geometry | Carbody and bogie point clouds | Alignment guidance, hold if out of tolerance |
| Readiness | Fit-out, bogie, coating state | Sequence and buffer plan |
| Test slots | Brake, traction, signaling, ride, haul | Commissioning schedule |
Multi-agent handoff
Agents negotiate, they do not collide
Two agents will want the same sequence slot. The orchestrator arbitrates on the run goal, not on who asked first, and the handoff is logged like any other step.
Contested move: car 07 marriage slot
-
01line_logistics.request(marry car07 at 10:40) SUCCEEDED0.2 s
Line-and-Logistics wants car 07 on the marriage station at 10:40 to hold the 13:40 brake-test slot.
-
02coat_livery.request(hold car07 to 11:05) SUCCEEDED0.2 s
Coat-and-Livery wants car 07 held until 11:05 because the second coat's cure window does not close until then.
-
03orchestrator.arbitrate SUCCEEDED0.4 s
A broken cure window is a repaint; a 25-minute slip still reaches the test slot. Under the run goal "livery inside the cure window", Coat-and-Livery wins. Marriage moves to 11:10, car 06 takes the earlier station time.
-
04line_logistics.handoff(resequenced) SUCCEEDED38 s
Sequence re-solved with the cure window as a hard constraint. Brake-test slot at 13:40 held; AMR routes updated.
Illustrative scenario.
Arbitration rules
- Run goal first. Every request is scored against the declared goal, not the requesting agent's local objective.
- Quality outranks cadence. A repaint or a weld rework costs more than a station slip the sequence can absorb.
- The envelope is never contested. Both requests must sit inside the approved control plan and work instructions; anything outside goes to a human.
- Time-boxed ownership. An agent holds a contested station or slot 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.
Autonomy
Four levels, set per agent and per tool
A rolling-stock plant does not go from manual to unattended in one step. Railira 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 actions. Weld parameters, schedule release and car release stay with named humans until acceptance is earned.
| Level | What the agent does | What the human does | Where it sits in a pilot |
|---|---|---|---|
| L1 · Shadow | Reads weld, metrology, torque, coating, wiring, test, robot and MES signals; predicts and recommends; writes nothing | Runs the line as today; compares predictions to inspection and engineer outcomes | Shadow mode; baseline measured from the plant's own records |
| L2 · Assist | Proposes weld-sequence, geometry, coating, torque and sequencing moves with evidence, confidence, envelope and rollback path | Approves each move in the review console | Assist mode; accuracy and ROI proven against the baseline |
| L3 · Bounded | Executes pre-approved low-risk actions: inspection routing, rework priority, kit feeding, robot path variants and parameter adjustments inside approved bounds | Approves heat-input and weld-sequence changes, schedule release and car release | Graduated autonomy, after audited accuracy and ROI and safety gates |
| L4 · Scaled | Supervised weld-parameter adaptation inside pre-approved control-plan envelopes, across lines and plants | Sets the envelope; reviews the shift record and the evaluation results | Planned; after IRIS, plant and OEM acceptance is earned |
Targets
Design targets, stated as targets
These are the figures in our compute plan and first-release plan. None is a measured result. Every pilot measures against the plant's own baseline, reproduced from its own rework, acceptance and line records, not from our telemetry.
100 to 500
GPU-hours per plant during onboarding · design target
50k to 250k
synthetic images or scan variants per rolling-stock program · design target
2 to 4
design-partner plants on the wedge workflow · plan
1
plant-edge runtime, one record per car, across every agent · design
Segments
Where plants start
Locomotives, high-speed and intercity trainsets, metro and commuter cars, passenger coaches, freight wagons. Most plants pick one process and one wedge, prove the number, then expand.
LocomotivesHeavy structures, high value
Locomotives
Locomotive carbody and underframe shops with large welded structures and propulsion integration. Carbra on the shell line first, where weld rework and geometry escapes are already counted.
High-speed and intercity trainsetsGeometry and ride quality
High-speed and intercity trainsets
Aluminium extrusion shells, tight door-aperture tolerances and ride-quality acceptance. Carbra and Bogira together, with Fitura on the marriage station.
Metro, light rail and commuter carsVariants and cadence
Metro, light rail and commuter cars
Variant-rich, long-cycle lines where a missed bogie or cure window breaks delivery cadence. Taktos on the shift plan, Coatyx on the booth.
Passenger coachesFit-out and livery
Passenger coaches
Interior fit-out, accessibility requirements and class-A livery. Fitura on fit-out and Coatyx on livery, with the conformance record from day one.
Freight wagonsVolume and torque
Freight wagons
High-volume welded structures and running-gear assembly at rate. Carbra and Bogira where the torque and weld records already exist.
Accelerated computing
Physical AI, at the station
A seam is welded in seconds and a booth cannot wait for the cloud. Perception has to be local, deterministic and fast, so Railira runs GPU inference at the plant edge and keeps training, simulation and optimisation in the cloud or on-prem.
Edge perception
8 to 32 cameras per process area plus metrology, torque, thermal, robot and booth-instrument streams fused at the plant edge. Sub-50 ms weld and seam alerts and sub-150 ms coating and metrology prompts are the design targets. Jetson Thor is planned for higher sensor density.
Model serving
Weld-defect, geometry-risk, coating-risk, point-cloud and takt-risk models served at the plant edge with per-model versioning and rollback, routed by latency, tenant, sensitivity and cost.
Training
Weld and coating defect vision, metrology classification, control-plan reasoning and FEA-surrogate models fine-tuned on plant data and engineer corrections. 100 to 500 GPU-hours per plant during onboarding is the design target; dedicated capacity is planned.
Train-and-plant twin
As-built carbody, coating, marriage and line-flow twin. Weld distortion, geometry build-up, robot reach, coating coverage and layout simulated before the shift. GPU FEA and point-cloud metrology are the workloads; OVX scale is planned.
Synthetic data
Rare weld defects, coating contamination, geometry deviations, occluded seams and torque-escape cases generated and validated against real inspection distributions before promotion. Planned.
Optimisation
Line sequencing, JIS feeding, AMR and AGV routing, buffer management and commissioning-slot scheduling against live readiness.
Robot cells
Robotic weld, coating and assembly cells and AMR or AGV flow; path variants validated in simulation before release to the floor.
GPU ETL
Telemetry features from weld parameters, metrology, coating readings, torque, non-conformance and takt history for retraining, drift detection and network analytics.
Developers
Define an agent, bound it, run it
The Railira SDK is typed Python. Tools are declared with schemas, limits and the approved control-plan envelope, and the policy engine enforces them at call time, not in a review meeting. This is a design preview; the API will change before release.
What you get
- Typed tool definitions with unit-aware ranges, rate limits and control-plan envelopes
- Deterministic replay of any historical run against a new model
- Local twin harness so a weld sequence or build order is simulated before it is shipped
- Autonomy policy as code, versioned and reviewed like any other change
# Design preview. Bound the weld agent to shell line B.
from railira import Agent, Tool, Limit, Autonomy
sequence = Tool(
name="weld.set_sequence",
targets=["B.ROOF_SEQ", "B.CLAMP_PLAN"],
limits=[Limit(envelope="control-plan M4-118", weld_class="EN15085-CP-C2")],
)
weld = Agent(
id="agent.weld_structure",
goal="door aperture within 1.5 mm, EN 15085 class per joint, least heat input",
tools=[sequence, Tool("seam.vision", read_only=True)],
# bounded recommendations on sequence; heat input stays with a human
autonomy=Autonomy.L3,
# simulate on the twin before every recommendation
verify="twin",
)
run = weld.start(line="B", car="M4-118-07")
for step in run.stream():
print(step.name, step.status, step.duration)
CLI
Start a run from anywhere
The same run engine, the same policy checks, the same audit trail, from the terminal, the review console or the SDK. Design preview.
$ railira run "car M4-118-07 through marriage" --autonomy L2+
→ plan composed 10 steps · 1 approval gate
→ cuopt.sequence shift A · cure window and 13:40 test slot held
→ twin.simulate 18 candidates · best #6 · aperture dev 0.6 mm
→ policy.evaluate 6 recommendations permitted · heat_input held for human
→ executing weld.sequence .... ok 3m12s
! approval required heat_input roof joints −2%
→ approved shift weld engineer · 06:12:44
→ executing bogie.torque ..... ok continuous
→ executing coat.cure ........ ok continuous
→ executing marry.align ...... ok 2m05s
→ scenario complete torque escapes 0 · car 07 released
$ railira runs show run_9b4e27 --format genealogy
Pricing
Priced per process, per plant, per network
Land on one workflow with a measured baseline. Expand by process, module and autonomy level. Outcome components are available on rework, line uptime, first-time-through and takt. Annual prepay carries a 15 to 20% discount.
Carbody, coating or assembly autonomy or inspection AI for one process. For plants validating ROI on the wedge.
- One process or line area, one agent module
- Plant-edge inference node included
- Controller and sensor reads, guarded recommendations
- Run log, audit trail, car genealogy
- Business-hours support
The whole plant: weld and structure, carbody and join, geometry and framing, coat and livery, marry and couple, fit-out and interior, quality and anomaly, line and logistics, and the twin.
- All agents on every process
- Fused inspection on every line
- Quality, conformance, line and takt
- Robotic cell and AMR supervision
- As-built train-and-plant twin
- 24/7 support, quarterly model review
Multi-plant OEM and tier-1 networks standardising on Railira, with custom carbody, coating, torque and takt models and a plant-edge fleet.
- Multi-plant fleet management
- Custom carbody, coating, torque and takt models
- Plant-edge fleet with on-prem option
- Group autonomy policy and approval chains
- SLAs, SSO and RBAC, dedicated engineer
Who it is for
Built for the people who run the plant
We have no customer quotes to show yet and will not invent any. These are the three roles in a rolling-stock plant we build for, and the problems they bring to the first meeting.
Owns launch dates, takt, line uptime, rework and cost.
What this person is dealing with today
- Periodic audits, offline metrology and sampled inspection that let geometry, weld, coating and torque quality drift
- Line stoppages and takt loss cascading across the build schedule
- A severe skilled-operator and quality-engineer shortage that cannot staff the launch cadence
Owns joining and coating processes, carbody geometry strategy, robot programming and process capability.
What this person is dealing with today
- Carbody shell distortion and fixture drift driving weld-defect scrap and downstream geometry problems
- Geometry build-up and alignment error costing rework, door and glazing leaks and ride quality
- Coating contamination, runs and film-thickness faults driving repaint and class-A livery rejects
Owns weld, coating, geometry and torque quality, non-conformance, PPAP, and IRIS / ISO/TS 22163 and TSI, AAR, APTA traceability.
What this person is dealing with today
- Marriage and coupling misalignment and torque escapes creating safety-critical rework and recall risk
- Traceability for IRIS and PPAP audits assembled by hand after the fact
- Carbody fabrication, bogie assembly, coating, fit-out and systems integration siloed and reactive
Integrations
It speaks plant, not cloud
Railira reads and writes through the systems already on the floor. No rip and replace, no parallel historian, no new HMI to learn. Vendor names are examples of systems found in rolling-stock plants, not certified integrations; connector availability is confirmed per site.
Rail PLM, MES and sequencing suites (Siemens Teamcenter, Opcenter and Tecnomatix, Dassault DELMIA, Rockwell, iBASEt, Critical Manufacturing class systems)
Work packages, control plans, sequence reads; genealogy and schedule write-back
Robot controllers and process controllers (FANUC, KUKA, ABB, Yaskawa, Comau, Dürr, Kawasaki class systems)
Parameter and path reads; bounded parameter and sequence recommendations
Laser trackers, point-cloud scanners and vision systems (Hexagon, Zeiss, FARO, Cognex, ISRA Vision, Perceptron class systems)
Geometry scans and inspection results per car
Torque tools and controllers (Atlas Copco, Bosch Rexroth, Stanley class systems)
Torque traces per joint, rework routing
Wiring testers, brake-test rigs, traction-test and ETCS, ERTMS or PTC commissioning systems
Continuity, brake and signaling results per car
Booth instruments, thickness gauges, environmental sensors, recipe systems
Film build, flash, cure, humidity and temperature
Plant-simulation and twin tools (Siemens Tecnomatix Plant Simulation, Dassault DELMIA, Visual Components)
Model and result exchange with the train-and-plant twin
Fleet managers and dispatch APIs
Fleet state, dispatch recommendations
Guardrails
An agent that can change a weld sequence needs a leash
Railira writes to production systems. Every capability is scoped, every write is policy-checked against the approved control plan, and every action is written to an append-only audit log the plant owns.
- Bounded action space. Each agent acts only through an explicit tool allow-list, inside per-tool rate and magnitude limits and the approved control-plan envelope for the car type.
- Policy engine before every write. Autonomy level, shift, car type, interlock state and operator presence are evaluated before a recommendation becomes a write to a robot, MES, torque tool or work package.
- Human-in-the-loop gates. Heat-input and weld-sequence changes, schedule release and car release wait for a named approver. High-risk changes remain human-approved until IRIS, plant and OEM acceptance is earned.
- Immutable audit log. Append-only and exportable. Every action records source evidence, the control-plan envelope, confidence, estimated quality and takt impact, rollback path, approver and car scope.
- Hard fallback. Loss of the edge node, the network or a model returns control to the robot, PLC or station's last known-good state. Safety systems and interlocks are never in Railira's path.
- Tenant and program isolation. Designs, control plans, program data, models and memory never cross a customer boundary. On-prem and plant-edge deployment is available for regulated plants.
Compliance posture
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I and OEM cyber review | 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 |
| IRIS and regulatory assurance packages | Disposition and genealogy evidence | QUEUED Planned, 6 to 12 months; not a certification claim |
| Standards-cited reasoning | Control plans, EN 15085, IRIS / ISO/TS 22163, TSI, AAR, APTA, torque and brake-test procedures | RUNNING In the design, every answer cites its source |
| Per-tenant and program isolation | Designs, control plans, models, memory | RUNNING In the design from day one |
| On-prem and plant-edge deployment | Regulated plants | RUNNING Design option |
Enterprise
Standardise autonomy across the network
One policy model, one audit trail, one benchmark across every process in every plant, with the carbody, coating, torque and takt models kept private to each site and program.
- SSO and role-based access down to the tool level, planned for the 6 to 12 month release
- Network-wide autonomy policy with per-site override and approval chains
- Cross-plant benchmarking on first-time-through, rework, PPM, delivery risk and takt
- On-prem and plant-edge deployment for regulated and OEM cyber-reviewed plants
- Edge autonomy that survives control-plane loss by returning to the controller's last known-good state
- Dedicated deployment engineer and quarterly model review per plant
FAQ
Straight answers
The questions plant directors, body and coating engineers and quality leads ask in the first meeting.
Only within an explicit tool allow-list with per-tool rate and magnitude limits, inside the approved control-plan envelope, and only at the autonomy level your plant has set. Design partners start in shadow mode, where Railira writes nothing. Heat-input and weld-sequence changes, schedule release and car release stay with a named approver.
Control returns to the robot, PLC or station's last known-good state. Railira is a supervisory layer on top of the controllers, safety systems and interlocks you already run, never a replacement for them, so an outage degrades the line to its current way of running, not to a stop.
Recommendations start from the control plan, the work instructions and the twin in the first weeks. Weld, geometry, coating and torque prediction improve as line history and labelled outcomes accumulate per car type. Onboarding is sized at 100 to 500 GPU-hours per plant and 50,000 to 250,000 synthetic images or scan variants per program, all design targets.
Only if you choose cloud training. Designs, control plans, program data, process models and quality records are isolated per tenant and never used to train another customer's models. Fully on-prem deployment at the plant edge is available for regulated plants, and cross-plant learning 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 on one process or line area, scoped to a single wedge with a success metric written into the order form: weld or coating rework reduction, geometry escapes, torque escapes, line stoppage minutes or first-time-through. It starts in shadow mode against a baseline from your own records, moves to assist mode when the engineer is satisfied, and expands only after the number moves.
Get started
Bring autonomy to your plant
Start with one carbody, bogie, coating, fit-out or sequencing process and one measurable baseline. A paid pilot on weld and geometry, torque assurance, livery defects or line sequencing shows the number before you commit further.