Security

How a piece of software is allowed to touch a line.

Draweon writes to production equipment, 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 plant owns, hard fallback to the controller, and isolation between tenants.

Ask a security question Read the docs

Policy before every writeAppend-only auditPer-tenant isolation

Every agent action records
  • Source signals it acted on
  • Procedures and specs it retrieved, with citations
  • Predicted impact
  • Allowed range and the limit applied
  • Rollback condition
  • Responsible approver
  • Reel and length scope

Nothing is written without this record.

Guardrails

An agent that can move a screw speed needs a leash

Draweon writes to production equipment. Every capability is scoped, every write is policy-checked, and every action is written to an append-only audit log the plant owns.

  • Bounded action space. Each agent writes only to an explicit tag allow-list, inside per-tag rate and magnitude limits.
  • Policy engine before every write. Autonomy level, shift, construction, interlock state and operator presence are evaluated before a setpoint moves.
  • Human-in-the-loop gates. Anything above the site threshold, such as line-speed ramps, die changes and reel release, waits for a named approver.
  • Immutable audit log. Append-only and exportable. Every action records source signals, retrieved procedures, predicted impact, allowed range, rollback condition, approver and reel scope.
  • Hard fallback. Loss of the edge node, the network or a model returns control to the line controller's last known-good state.
  • Tenant and IP isolation. Construction recipes, defect libraries and process memory never cross a customer boundary. On-prem deployment is available for sensitive producers.

Compliance posture

ItemScopeStatus
SOC 2 Type ICloud control plane QUEUED Planned, first 6 months
SOC 2 Type IICloud control plane QUEUED Planned, 6 to 12 months
SSO and RBACConsole and approvals QUEUED Planned, 6 to 12 months
Standards-cited reasoningUL, IEC, IPC, USCAR documents RUNNING In the design, every answer cites its source
Per-tenant isolationRecipes, models, memory RUNNING In the design from day one
On-prem and plant-edge deploymentSensitive producers RUNNING Design option

Read the security overview

Data

What data exists and who can see it

The data strategy from the architecture: reel-based, labelled from the line, synthetic only for rare defects, governed per tenant.

Sources

  • Camera frames, laser diameter and eccentricity traces
  • Eddy-current and spark-test events, PLC tags, line speed, tension, die sequence
  • Annealing current, conductivity tests, extrusion temperatures and pressures, cooling
  • Stranding lay, reel metadata, operator approvals, quality outcomes, scrap reasons, energy use, customer conformance

Governance

  • Tenant isolation for recipes, models and memory
  • Recipe redaction and data-rights controls
  • Model cards and dataset versioning
  • Traceable consent before any cross-plant learning, which is planned and not yet in place
  • Synthetic data used only to augment rare defects, validated against real distributions
OT safety

The write path

What has to be true before a setpoint moves.

  1. A declared tool. The agent can only call tools declared with tags, units and limits.
  2. A policy decision. Autonomy level, shift, construction, interlock state and operator presence are evaluated.
  3. A simulated check. Where the agent is configured with verify=twin, the move is simulated before it is written.
  4. An approval, if required. Anything above the plant's threshold waits for the named approver.
  5. A bounded write. The connector enforces per-tag rate and magnitude limits again at the OT boundary.
  6. A record. The action, its evidence and its outcome are appended to the audit log and the reel genealogy.
  7. A rollback path. Declared rollback conditions return the tag to its previous value or the controller to last known-good.
Autonomy

Four levels, set per agent and per tag

A plant does not go from manual to unattended in one step. Draweon makes the level explicit, auditable and reversible at any time. The first release runs shadow mode, then assist mode, then graduated autonomy.

Autonomy levels and the human role at each
LevelWhat the agent doesWhat the human doesWhere it sits in a pilot
L1 · AdvisoryRecommends setpoints and explains why, with citationsEnters every change manuallyShadow mode, weeks 1 to 3
L2 · SupervisedProposes a write; it executes on approvalApproves each write in the review consoleAssist mode, weeks 4 to 8
L3 · BoundedWrites inside tag, rate and magnitude limitsApproves ramps, die changes and reel releaseGraduated autonomy, from week 9 if the plant is satisfied
L4 · UnattendedRuns the envelope without promptingSets the envelope; reviews the shift recordPlanned; after qualification on the construction
Run timeline · scenario

One scenario run, step by step

Every Draweon run is an ordered, inspectable sequence. This is run_3d7a1e on EX-3 · 2.5 mm² class 2 PVC building wire. Scenario completes in 10 steps with one approval gate. Wall settles at 0.80 mm nominal, minimum 0.66 mm, concentricity 0.93, no spark faults, reel R-30417 released with full genealogy.

run_3d7a1e EX-3 · 2.5 mm² class 2 PVC building wire illustrative scenario SUCCEEDED
  1. 01 ingest.order SUCCEEDED 0.6 s

    Plant Orchestrator · Pulled the construction spec for 2.5 mm² class 2 PVC building wire from MES: 7 × 0.67 mm conductor, 0.80 mm nominal wall, 0.62 mm minimum spot wall, 6 kV spark test, 48 km order. Locked the target envelope.

  2. 02 twin.simulate SUCCEEDED 41 s

    Line Twin · Simulated 36 candidate recipes on the as-run line twin for draw schedule, lay length and extrusion setpoints, ranked on wall variance, concentricity, predicted spark risk and polymer give-away.

  3. 03 draw.tension SUCCEEDED 1 m 48 s

    Draw-and-Anneal · Capstan tension on RB1 stepped down 6% as the die-wear estimate crossed its threshold. Diameter held at 0.670 mm ± 0.004 mm and the break-risk score fell from 0.31 to 0.09.

  4. 04 anneal.current SUCCEEDED 54 s

    Draw-and-Anneal · Annealer current trimmed against the live conductivity reading to hold the softness target without over-anneal through the speed change.

  5. 05 strand.lay SUCCEEDED 1 m 12 s

    Strand-and-Cable · Lay length set to 28 mm on bunching line ST2 with payoff tension balanced across 7 spools. Roundness index held above 0.97 into the extrusion payoff.

  6. 06 extrude.wall SUCCEEDED 2 m 36 s

    Insulate-and-Jacket · Screw speed and zone 3 temperature re-cut against melt pressure and material-lot moisture. Wall settled at 0.80 mm nominal, minimum 0.66 mm, concentricity 0.93.

  7. 07 inspect.fuse SUCCEEDED continuous

    Defect-and-Inspect · 6 cameras, the laser gauge, the eddy-current head and the spark tester fused at the edge. One neckdown precursor at 12,480 m flagged and cleared by a screw-speed trim before it reached the reel.

  8. 08 approve.human APPROVAL 38 s

    Plant Orchestrator · Line-speed ramp 1,100 to 1,250 m/min exceeded the site autonomy threshold. Held for the shift process engineer and approved at 06:41:52.

  9. 09 reel.change SUCCEEDED 2 m 05 s

    Robot-and-Handling · Reel change on take-up TU3 planned and executed by the handling robot. Payoff aligned and tension re-established inside the changeover window.

  10. 10 reel.release SUCCEEDED 1 m 10 s

    Quality-and-Conformance · Reel R-30417 released: genealogy written (conductor lot, draw and anneal record, lay, wall and concentricity trace, defect map, approvals) and checked against the construction spec.

Tool calls · scenario

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 plant.

tool-call stream · run_3d7a1e
  1. 06:30:12mes.read_order({ line: "EX-3", construction: "BW-2.5-C2-PVC" })
  2. 06:30:12ok spec locked · wall 0.80 mm nominal · min 0.62 mm · spark 6 kV
  3. 06:30:13twin.simulate({ candidates: 36, horizon: "14 min" })
  4. 06:30:54ok best recipe #22 · wall var 0.018 · spark risk 0.04 · give-away 2.1%
  5. 06:30:55policy.evaluate({ recipe: 22, autonomy: "L3" })
  6. 06:30:55ok 8 writes permitted · 1 write requires human approval
  7. 06:30:56plc.write_setpoint({ tag: "RB1.CAPSTAN_T", delta: "-6%" })
  8. 06:32:44ok diameter 0.670 mm ±0.004 · break risk 0.31 → 0.09
  9. 06:32:45plc.write_setpoint({ tag: "ANN1.CURRENT", mode: "hold_conductivity" })
  10. 06:33:39ok conductivity on target · softness in window
  11. 06:33:40plc.write_setpoint({ tag: "ST2.LAY", to: "28 mm", spools: 7 })
  12. 06:34:52ok roundness 0.97 · payoff tension balanced
  13. 06:34:53plc.write_setpoint({ tag: "EX3.SCREW_RPM", zone3: "+4 °C" })
  14. 06:37:29ok wall 0.80 nominal · min 0.66 · concentricity 0.93
  15. 06:37:30sensors.fuse({ cams: 6, laser: true, eddy: true, spark: true })
  16. 06:39:04precursor: neckdown risk 0.58 · 12,480 m · zone 3
  17. 06:39:05plc.write_setpoint({ tag: "EX3.SCREW_RPM", delta: "+1.5%" })
  18. 06:39:21ok neckdown risk 0.58 → 0.06 · wall recovered
  19. 06:39:22approval.request({ action: "line_speed", to: "1250 m/min" })
  20. 06:41:52ok approved by shift process engineer · logged
  21. 06:41:53isaac.plan_path({ task: "reel_change", takeup: "TU3" })
  22. 06:43:58ok reel changed · payoff aligned · tension re-established
  23. 06:43:59mes.log_reel({ reel: "R-30417", genealogy: "full" })
  24. 06:45:09ok scenario complete · 10 steps · spark faults 0 · released

Reasoning trace

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

GoalChange line EX-3 over to 2.5 mm² class 2 PVC building wire, ho…

Change line EX-3 over to 2.5 mm² class 2 PVC building wire, hold 0.80 mm nominal wall and concentricity, and finish the run with zero spark faults.

PlanSimulate the changeover on the twin first. Lead with drawing a…

Simulate the changeover on the twin first. Lead with drawing and annealing so the conductor is right before stranding, then set lay, then re-cut extrusion against the live wall reading. Fuse inspection continuously. Hold the line-speed ramp for a human.

ThoughtThe standing recipe raises line speed and screw speed together…

The standing recipe raises line speed and screw speed together. On the twin that produces a wall dip at zone 3 because the melt pressure lags the speed step. Sequencing the zone 3 temperature move ahead of the speed ramp removes it.

Actiontwin.simulate(candidates=36) returns recipe #22: zone 3 up 4 °…

twin.simulate(candidates=36) returns recipe #22: zone 3 up 4 °C before the ramp, screw speed trimmed to the live wall reading, lay 28 mm.

ObservationRecipe #22 predicts wall variance 0.018 mm, spark risk 0.04 an…

Recipe #22 predicts wall variance 0.018 mm, spark risk 0.04 and give-away 2.1%. Three candidates scored lower on give-away but pushed predicted minimum wall under the spec floor and were discarded.

ActionExecute recipe #22 under autonomy level L3: eight setpoint wri…

Execute recipe #22 under autonomy level L3: eight setpoint writes permitted, the line-speed ramp routed to the shift process engineer.

ObservationNeckdown precursor at 12,480 m at 06:39:04. A 1.5% screw-speed…

Neckdown precursor at 12,480 m at 06:39:04. A 1.5% screw-speed trim cleared it in 16 s with no reel quarantined.

OutcomeScenario complete. Wall 0.80 mm nominal, minimum 0.66 mm, conc…

Scenario complete. Wall 0.80 mm nominal, minimum 0.66 mm, concentricity 0.93, zero spark faults. Reel R-30417 released with full genealogy.

Enterprise

Standardise autonomy across the group

One policy model, one audit trail, one benchmark across every line in every plant, with the conductor, insulation and tolerance models kept private to each site.

Talk to us Enterprise details

  • SSO and role-based access down to the tag level, planned for the 6 to 12 month release
  • Group-wide autonomy policy with per-site override and approval chains
  • Cross-plant benchmarking on scrap, give-away, breaks, energy and first-pass quality
  • On-prem and plant-edge deployment, with air-gapped operation for sensitive producers
  • 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 and process engineers ask in the first meeting.

Yes, but only within an explicit tag allow-list with per-tag rate and magnitude limits, and only at the autonomy level your plant has set. Level 1 is advisory: Draweon recommends and a human enters everything. Design partners start there, in shadow mode, before supervised writes.

Get started

Send us your security questionnaire

We answer plainly, including where an item is planned rather than done.

Contact Enterprise