How a piece of software is allowed to touch a welding robot.
Hullira writes to production equipment in yards that build naval and class-surveyed vessels, so the security story is mostly a control story: a bounded action space, a policy engine before every write, named approvers, an append-only audit log the yard owns, hard fallback to the controller and its interlocks, and defense-aware isolation between tenants and their drawings.
- Source evidence it acted on
- WPS, class rules, PSPC and procedures it retrieved, with citations
- The qualified envelope and the limit applied
- Confidence and estimated rework, dock-time and schedule impact
- Rollback path
- Responsible approver
- Block and area scope
Nothing is written without this record.
An agent that can move a weld parameter needs a leash
Hullira writes to production equipment. Every capability is scoped, every write is policy-checked against the qualified WPS, class and PSPC constraints, and every action is written to an append-only audit log the yard owns.
- Bounded action space. Each agent writes only to an explicit tag allow-list, inside per-tag rate and magnitude limits and the qualified WPS, coating, dimensional and schedule constraints for the block.
- Policy engine before every write. WPS and PQR, class rules, PSPC, safety limits, role permissions, autonomy level and human-approval requirements are evaluated before a parameter moves. NeMo Guardrails is the design for this layer.
- Human-in-the-loop gates. Class-critical seam changes, lift plans, block release and class evidence wait for a named approver. Robots adapt only inside pre-approved WPS envelopes until class, yard and insurer acceptance supports more.
- Immutable audit log. Append-only, assurance-grade and exportable. Every action records source evidence, the WPS, class or PSPC citation applied, confidence, estimated rework, dock-time and schedule impact, rollback path, approver and block scope.
- Hard fallback. Loss of the edge node, the network or a model returns control to the robot controller, PLC or planner's last known-good state. Interlocks are never in Hullira's path.
- Tenant and defense-aware isolation. Drawings, WPS, naval data, models and memory never cross a customer boundary. Security is defense and ITAR-aware, and on-prem or yard-edge deployment is available for naval and regulated yards.
Compliance posture
| Item | Scope | Status |
|---|---|---|
| SOC 2 Type I | Cloud control plane | QUEUED Planned, first 6 months, with a defense and ITAR-aware review |
| 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 |
| Class-society and defense assurance packages | Disposition and genealogy evidence | QUEUED Planned, 6 to 12 months; not a class approval or certification claim |
| Cited reasoning | WPS and PQR, ABS, DNV, LR, ClassNK, IMO PSPC, naval specs | RUNNING In the design, every answer cites its source |
| Per-tenant and IP isolation | Drawings, WPS, naval data, models, memory | RUNNING In the design from day one |
| On-prem and yard-edge deployment | Naval and regulated yards | RUNNING Design option |
What data exists and who can see it
The data strategy from the architecture: block-based, labelled from the floor, synthetic only for rare cases, governed per tenant with defense controls.
Sources
- Weld-pool and seam video, robot parameters, WPS and PQR, material heat and plate geometry
- X-ray and UT files, laser scans, photogrammetry, fairing corrections
- Coating environmental readings and dry-film-thickness measurements
- Crane and dock schedules, block genealogy, non-conformance reports, class comments and operator approvals
Governance
- Tenant isolation for drawings, WPS, naval data, models and memory
- Defense and ITAR-aware security, IP-safe deployment and data-rights controls
- Model lineage, action replay and exportable class evidence
- Traceable consent before any cross-yard learning, which is planned and not yet in place
- Synthetic data used only to augment rare defects and unsafe cases, validated against real distributions
The write path
What has to be true before a parameter moves.
- A declared tool. The agent can only call tools declared with tags, units, limits and a WPS, coating or dimensional envelope.
- A policy decision. WPS and PQR, class rules, PSPC, safety limits, role permissions, autonomy level and human-approval requirements are evaluated.
- A simulated check. Where the agent is configured with verify=twin, the move is simulated on the ship twin before it is written.
- An approval, if required. Class-critical seam changes, lift plans, block release and class evidence wait for the named approver.
- A bounded write. The connector enforces per-tag rate and magnitude limits again at the OT boundary. Robot controllers, PLCs and safety interlocks are never in Hullira's path.
- A record. The action, its evidence and its outcome are appended to the audit log and the block genealogy.
- A rollback path. Declared rollback conditions return the tag to its previous value or the controller to last known-good.
Four levels, set per agent and per tag
A yard does not go from paper travelers to unattended welding in one step. Hullira makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then supervised control on low-risk actions. Class-critical seam changes, lift plans and block release stay with named people.
| Level | What the agent does | What the human does | Where it sits in a pilot |
|---|---|---|---|
| L1 · Shadow | Reads weld, scan, NDT, coating, robot, crane and MES signals; predicts and recommends; writes nothing | Runs the process as today; compares predictions to NDT and surveyor outcomes | Shadow mode; the baseline is measured from the yard's own records |
| L2 · Assist | Proposes weld, fairing, coating, routing and schedule moves with evidence, confidence, envelope and rollback path | Approves each action in the review console | Assist mode, the remainder of the pilot |
| L3 · Supervised control | Executes pre-approved low-risk actions: inspection routing, coating pauses when a window drifts, weld parameters inside the WPS envelope, robot path variants tested in simulation | Approves class-critical seam changes, lift plans and block release | Graduated autonomy, after audited accuracy and ROI |
| L4 · Bounded | Supervised work sequencing and weld adaptation for qualified block types, across processes and yards | Sets the envelope; reviews the shift record and the evaluation results | Planned; after class, yard and insurer acceptance is earned |
One scenario run, step by step
Every Hullira run is an ordered, inspectable sequence. This is run_4b7e19 on Block B-214 · double-bottom block · panel line PL-2 · dock D1. Scenario completes in 10 steps with one approval gate. Predicted distortion at the erection joint fell from 4.2 mm to 1.8 mm after a back-step sequence, one porosity precursor on seam S-31 was cleared inside the WPS envelope, the ballast-tank coat ran inside a 3.4 °C dew-point margin, and the block landed at 1.6 mm with its conformance record written.
-
01
ingest.package
SUCCEEDED
0.8 s
Yard Orchestrator · Pulled the work package for B-214 from the yard MES: 46 plates, 212 seams under WPS-117, erection tolerance 2 mm at the D1 joint, PSPC-grade ballast-tank coating, erection slot on D1 in the dock plan. Locked the qualified WPS envelope and the class scope.
-
02
twin.simulate
SUCCEEDED
1 m 12 s
Ship Twin · Simulated 18 candidate weld sequences on the as-built twin with the weld-thermal surrogate, ranked on predicted distortion at the erection joint, crane reach on D1 and shift takt. Standing sequence predicts 4.2 mm; candidate #6 predicts 1.8 mm.
-
03
cut.nest
SUCCEEDED
3 m 40 s
Cut-and-Profile · Released the nest for 46 plates on CL-1 with the fit-up gaps candidate #6 assumes. As-cut geometry logged per plate and handed to the panel line; material yield 91.4% against the nest plan.
-
04
weld.sequence
SUCCEEDED
2 m 05 s
Panel-and-Weld · Loaded the back-step sequence for the non-critical seams on PL-2 and set heat input and travel speed inside WPS-117. Weld-pool and seam cameras streaming on 12 channels.
-
05
approve.human
APPROVAL
58 s
Yard Orchestrator · Candidate #6 also re-orders two class-critical butt seams, S-31 and S-32. Sequence changes on class-critical seams stay with a human, so the step was held for the shift welding engineer and approved at 06:12:44.
-
06
inspect.fuse
SUCCEEDED
continuous
Quality-and-Anomaly · Twelve weld cameras and the UT station fused at the yard edge. One porosity precursor on S-31 at 06:41 flagged and cleared by a 4% wire-feed trim inside the WPS-117 envelope; the joint was routed to UT and passed.
-
07
fair.lineheat
SUCCEEDED
4 m 30 s
Fair-and-Form · Post-weld scan registered against the twin: 2.1 mm at the erection joint. Two line-heating passes planned on the inner bottom and executed by the fairing crew; re-scan read 1.8 mm, inside the 2 mm tolerance.
-
08
coat.window
SUCCEEDED
continuous
Blast-and-Coat · Ballast-tank blast and first coat scheduled to a window with steel temperature 3.4 °C above dew point. Dry-film thickness read 312 µm against a 280 µm minimum on the stripe coats; PSPC evidence assembled per area.
-
09
dock.reoptimise
SUCCEEDED
41 s
Schedule-and-Yard · Re-solved the D1 dock and crane plan with B-214 ready 6 hours early and a neighbouring block late: erection slot pulled forward one shift, crane G2 reassigned, no berth conflict. Planner approved the revised plan.
-
10
erect.align
SUCCEEDED
1 h 48 m
Erect-and-Align · Both blocks scanned on D1 and registered against the twin; fit predicted at 1.6 mm. Shimming guidance issued to the erection crew, block landed and welded out, final scan 1.6 mm. Conformance record written: welds, scans, coating readings, approvals and class evidence for B-214.
What the audit log looks like
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 yard or the surveyor.
- 06:04:10mes.read_packages({ block: "B-214", dock: "D1" })
- 06:04:11ok 46 plates · 212 seams · WPS-117 · 2 mm at D1 joint
- 06:04:12twin.simulate({ candidates: 18, objective: "distortion, reach, takt" })
- 06:05:24ok best #6 · joint 1.8 mm · reach ok · takt +0.4 h
- 06:05:25policy.evaluate({ plan: 6, autonomy: "L2+" })
- 06:05:25ok 8 writes permitted · class-critical seam order requires human approval
- 06:05:26cutter.set_program({ machine: "CL-1", nest: "B214-N3" })
- 06:09:06ok 46 plates cut · yield 91.4% · geometry logged
- 06:09:07weld.set_sequence({ line: "PL-2", plan: 6, scope: "non-critical" })
- 06:11:12ok back-step loaded · heat input inside WPS-117
- 06:11:46approval.request({ action: "seam_sequence", seams: ["S-31", "S-32"] })
- 06:12:44ok approved by shift welding engineer · logged
- 06:12:45sensors.fuse({ cams: 12, ut: true })
- 06:41:03precursor: porosity risk 0.57 · seam S-31 · 1.2 m from start
- 06:41:04robot.set_parameters({ cell: "PL-2.R3", wire_feed: "-4%", within: "WPS-117" })
- 06:41:19ok porosity risk 0.57 → 0.09 · S-31 routed to UT · passed
- 09:20:30scan.register({ block: "B-214", stage: "post-weld" })
- 09:21:02ok joint 2.1 mm · 2 line-heat passes planned
- 11:02:40ok re-scan 1.8 mm · inside 2 mm tolerance
- 11:02:41coat.schedule_area({ area: "BT-214", spec: "PSPC" })
- 11:02:42ok window open · steel 3.4 °C above dew point · DFT 312 µm
- 11:03:00cuopt.solve({ dock: "D1", horizon: "14d" })
- 11:03:41ok slot pulled forward 1 shift · crane G2 reassigned · planner approved
- 14:30:12align.guide({ block: "B-214", dock: "D1" })
- 16:18:40ok landed 1.6 mm · conformance record written · scenario complete
Reasoning trace
Plan, thought, action, observation, exactly as the orchestrator would record it.
GoalBuild and erect B-214 inside WPS-117, hold the erection joint …
Build and erect B-214 inside WPS-117, hold the erection joint within 2 mm, coat the ballast tank inside the PSPC window, and land it on D1 by the dock plan.
PlanSimulate weld sequences on the twin first. Lead with the seque…
Simulate weld sequences on the twin first. Lead with the sequence because distortion is decided at the arc, then cut to the fit-up the sequence assumes, then weld and inspect continuously. Scan after welding and fair only what the scan shows. Hold any class-critical seam change for a human.
ThoughtThe standing sequence welds the inner bottom straight through …
The standing sequence welds the inner bottom straight through and predicts 4.2 mm at the joint, which means fairing hours and a risk to the D1 slot. A back-step sequence with two class-critical seams re-ordered predicts 1.8 mm at a cost of 0.4 hours of takt.
Actiontwin.simulate(candidates=18) returns plan #6: back-step on the…
twin.simulate(candidates=18) returns plan #6: back-step on the non-critical seams, S-31 and S-32 re-ordered, heat input held inside WPS-117.
ObservationPlan #6 predicts 1.8 mm at the joint and clear crane reach on …
Plan #6 predicts 1.8 mm at the joint and clear crane reach on D1. Three candidates scored lower on distortion but moved heat input outside the WPS envelope and were discarded.
ActionExecute plan #6: eight bounded writes permitted on cutting, no…
Execute plan #6: eight bounded writes permitted on cutting, non-critical weld sequence, parameters inside WPS, coating windows and dock plan; the class-critical seam order routed to the shift welding engineer.
ObservationPorosity precursor on S-31 at 06:41:03. A 4% wire-feed trim in…
Porosity precursor on S-31 at 06:41:03. A 4% wire-feed trim inside WPS-117 cleared it in 15 s; the joint was routed to UT and passed. Post-weld scan 2.1 mm, two line-heating passes brought it to 1.8 mm.
OutcomeScenario complete. Block landed at 1.6 mm, ballast tank coated…
Scenario complete. Block landed at 1.6 mm, ballast tank coated inside the window, conformance record written for class review.
Standardise autonomy across the group
One policy model, one audit trail, one benchmark across every process in every yard, with the weld, distortion and schedule models kept private to each site and each naval program.
- SSO and role-based access down to the tag level, planned for the 6 to 12 month release
- Group-wide autonomy policy with per-yard override and approval chains
- Cross-yard benchmarking on rework, fairing hours, coating non-conformance, dock days and schedule slips
- On-prem and yard-edge deployment, defense and ITAR-aware, for naval and regulated yards
- 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 yard
Straight answers
The questions production directors, welding engineers and class-compliance leads ask in the first meeting.
Yes, but only within an explicit tag allow-list with per-tag rate and magnitude limits, inside the qualified WPS, coating, dimensional and schedule constraints, and only at the autonomy level your yard has set. Design partners start in shadow mode, where Hullira writes nothing. Class-critical seam changes, lift plans and block release stay with named people.
Control returns to the robot controller, PLC or planner's last known-good state. Hullira is a supervisory layer on top of the controllers and interlocks you already run, never a replacement for them, so an outage degrades the process to its current way of running, not to a stop.
Advisory recommendations start from the physics-based twin, the WPS and the block drawings in the first weeks. Defect, distortion and coating prediction improve as block history and labelled NDT and surveyor outcomes accumulate. Onboarding is sized at 100 to 500 GPU-hours per yard and 50,000 to 250,000 synthetic variants per vessel class, both design targets.
Only if you choose cloud training. Drawings, WPS and PQR, naval data, process models and quality records are isolated per tenant and never used to train another customer's models. Security is defense and ITAR-aware, a fully on-prem deployment at the yard edge is available for naval and regulated yards, and federated learning across yards is planned and waits on data-rights agreements.
You are, the same as with any procedure change, 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 WPS or class citation applied and the human decision.
A paid pilot on one process, scoped to a single wedge with a success metric written into the order form: weld rework, fairing hours, coating non-conformance, dock days or class-approval cycle time. Shadow mode comes first and the baseline is measured from your own records. We do not publish a pilot length because we have not run one.
Send us your security questionnaire
We answer plainly, including where an item is planned rather than done.