Documentation

Everything needed to run, extend and audit the platform.

Getting started, reference, runbooks, the autonomy model, the CLI and the platform limits. The documentation describes the design; sections marked design preview will change before release.

Getting startedReferenceRunbooks

run_41a9c2 · agent graph · plant BIW-2 · scenario 10 nodes · 1 approval gate
01 · orchestrator ingest.shift ✓ SUCCEEDED 02 · vehicle_line twin.simulate ✓ SUCCEEDED 03 · stamp_form stamp.form ✓ SUCCEEDED 04 · orchestrator approve.human ◆ APPROVAL 05 · weld_join weld.join ✓ SUCCEEDED 06 · frame_geometry frame.geometry ✓ SUCCEEDED 07 · paint_finish paint.finish ✓ SUCCEEDED 08 · powertrain_battery marriage.torque ✓ SUCCEEDED 09 · quality_anomaly inspect.fuse ✓ SUCCEEDED 10 · eol_calibrate eol.release ✓ SUCCEEDED

Illustrative scenario: Plant BIW-2 · EV crossover body shop to end of line · shift 1, one approval gate

Getting started

First hour

From an empty plant-edge node to a shadow-mode run.

  1. Install the plant-edge runtime. A Jetson Orin node with the Chassira runtime image, inside the plant network.
  2. Connect read-only sources. Robot and servo-gun traces, in-line metrology, booth instruments, torque tools, test stands, cameras and MES, all read-only.
  3. Define the program. Load the control plan: joint families and weld schedules, framing targets, colour blocks and booth windows, torque specifications (locked), test limits (locked), qualified envelopes.
  4. Create an agent at L1. Declare its tools read-only and let it watch and recommend.
  5. Start a shadow run. Observe the run record, the tool-call stream and the reasoning trace against the live line.
Developers

Define an agent, bound it, run it

The Chassira SDK is typed Python. Tools are declared with schemas, limits and the qualified envelope, the policy engine enforces them at call time, not in a review meeting, and safety-critical parameters are locked for every agent. This is a design preview; the API will change before release.

What you get

  • Typed tool definitions with unit-aware ranges, rate limits and qualified envelopes
  • Locked parameters: torque specifications, battery-joint parameters and test limits cannot be declared writable
  • Deterministic replay of any historical shift against a new model
  • Local twin harness so a sequence or window is simulated before it is shipped
  • Autonomy policy as code, versioned and reviewed like any other change

Read the docs Developer guide

b2_paint_agent.py
# Design preview. Bound the paint agent to booth B-2; weld schedules stay with a human.
from chassira import Agent, Tool, Limit, Autonomy

booth = Tool(
    name="booth.set_env",
    tags=["B2.HUMIDITY_PCT", "B2.AIRFLOW_M3H"],
    limits=[Limit(max_step="2 pt", per="10min", envelope="EV-CUV-dark-block")],
)

paint = Agent(
    id="agent.paint_finish",
    goal="film build in window, dirt and run risk minimised, zero repaint escapes",
    tools=[booth, Tool("filmbuild.read", read_only=True)],
    # bounded writes on booth environment
    autonomy=Autonomy.L3,
    # simulate on the plant twin before every write
    verify="twin",
)

# torque specifications and test verdicts are locked for every agent
run = paint.start(plant="BIW-2", shift=1)
for step in run.stream():
    print(step.name, step.status, step.duration)
Reference

Reference sections

What each section of the reference covers.

Agents

Definition and lifecycle

Agent, goal, tools, autonomy, verify, start, stream, replay.

Tools and limits

Connectors with schemas

Tag naming, units, read_only, locked, Limit(max_step, per, floor, ceiling, envelope).

Policy

Autonomy as code

Levels, approval routing, shift, program and interlock conditions, locked parameters, versioning and review.

Runs

The run record

Steps, status values (queued, running, waiting, approval, succeeded, failed, blocked), durations, outcomes.

As-built record

The vehicle record

Fields, export formats, retention, IATF, APQP and warranty evidence packets.

Twin

Simulation API

twin.simulate, candidates, horizon, ranking objectives, as-built comparison.

Run timeline · scenario

Reading a run record

Every Chassira run is an ordered, inspectable sequence. This is run_41a9c2 on Plant BIW-2 · EV crossover body shop to end of line · shift 1. Scenario completes in 10 steps with one approval gate. Weld schedule change on robot W-14 approved by the body-shop launch engineer, framing offset held inside the envelope, booth humidity trimmed before the predicted dirt defects appeared, one pack held at marriage on a torque trace, and the shift released with full as-built records.

run_41a9c2 Plant BIW-2 · EV crossover body shop to end of line · shift 1 illustrative scenario SUCCEEDED
  1. 01 ingest.shift SUCCEEDED 0.8 s

    Plant Orchestrator · Pulled the shift build sequence, program control plan and qualified envelopes from MES: 412 bodies, four trim variants, weld schedule set W-rev 7, framing targets per station, paint colour blocks, torque specifications. Locked every safety-critical parameter as read-only.

  2. 02 twin.simulate SUCCEEDED 1 m 40 s

    Vehicle-and-Line Twin · Simulated 18 candidate weld-sequence, framing-offset and booth-window combinations on the plant twin, ranked on predicted body geometry, expulsion risk at robot W-14, paint defect map and takt against launch cadence.

  3. 03 stamp.form SUCCEEDED continuous

    Stamp-and-Form · Blank feed on press line P-3 adjusted by 0.4 mm and lubricant dose raised 3 percent for the new coil lot as springback risk on the rear door inner climbed. Panel dimension held inside the window; genealogy handed to framing.

  4. 04 approve.human APPROVAL 3 m 12 s

    Plant Orchestrator · Candidate #6 lowers weld current 2 percent and adds 20 ms hold on robot W-14 to cut predicted expulsion. Weld schedules are crash-safety critical and stay with a human, so the change was held for the body-shop launch engineer and approved at 06:14:52.

  5. 05 weld.join SUCCEEDED continuous

    Weld-and-Join · Approved schedule 7b applied on W-14. Current and force traces confirmed inside the window on the first 40 bodies; predicted expulsion risk fell from 0.31 to 0.06 and no geometry debt was introduced at the adjacent seams.

  6. 06 frame.geometry SUCCEEDED continuous

    Frame-and-Geometry · Framing station FS-1 offset corrected by 0.3 mm on the left B-pillar datum inside the qualified envelope as in-line measurement trended toward the tolerance edge. Gap-and-flush vision confirmed the correction on the next 25 bodies.

  7. 07 paint.finish SUCCEEDED continuous

    Paint-and-Finish · Booth B-2 humidity trimmed 2 points and airflow rebalanced for the dark-colour block as the defect model predicted dirt on horizontal panels. Film build held inside the window on the first colour block.

  8. 08 marriage.torque SUCCEEDED continuous

    Powertrain-and-Battery · Pack PK-1182 held at marriage after a torque-to-yield trace on fastener 7 fell outside the specification curve. Routed to rework with the trace attached; torque specification untouched, as always.

  9. 09 inspect.fuse SUCCEEDED continuous

    Quality-and-Anomaly · Gap-and-flush and paint-defect cameras, weld and torque traces and test results fused per body. Two paint dirt defects localised to booth B-2 zone 3 before the humidity trim took effect; both routed to spot repair, none escaped to final.

  10. 10 eol.release SUCCEEDED 2 m 05 s

    EOL-and-Calibrate · End of line proved alignment, ADAS calibration, leak, brake, roll and functional tests on every vehicle; two ADAS retests sequenced inside takt. Shift 1 released with as-built records, approvals and dispositions written for the quality lead.

Tool calls · scenario

Reading the tool log

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_41a9c2
  1. 06:00:02mes.read_sequence({ plant: "BIW-2", shift: 1, program: "EV-CUV" })
  2. 06:00:03ok 412 bodies · 4 variants · weld set W-rev 7 · torque specs read-only
  3. 06:00:04twin.simulate({ candidates: 18, horizon: "1 shift" })
  4. 06:01:44ok best #6 · geometry inside targets · expulsion risk 0.06 · takt 61 s
  5. 06:01:45policy.evaluate({ candidate: 6, autonomy: "L2+" })
  6. 06:01:45ok 6 writes permitted · weld_schedule requires human approval · torque_spec locked
  7. 06:01:46blank.set_feed({ press: "P-3", delta: "+0.4 mm", lube: "+3%" })
  8. 06:02:30ok springback risk 0.42 → 0.11 · panel dimension in window
  9. 06:02:31approval.request({ action: "weld_schedule", robot: "W-14", current: "-2%", hold: "+20 ms" })
  10. 06:14:52ok approved by body-shop launch engineer · logged
  11. 06:14:53weld.apply_schedule({ robot: "W-14", rev: "7b" })
  12. 06:48:10ok 40 bodies in window · expulsion risk 0.31 → 0.06
  13. 06:48:11frame.set_offset({ station: "FS-1", datum: "B-pillar L", delta: "-0.3 mm" })
  14. 07:12:44ok 25 bodies inside targets · gap-and-flush confirmed
  15. 07:12:45booth.set_env({ booth: "B-2", humidity: "-2 pt", airflow: "rebalance" })
  16. 07:40:02precursor: dirt risk 0.58 · booth B-2 zone 3 · dark colour block
  17. 07:40:03ok 2 defects localised · routed to spot repair · 0 escaped
  18. 08:05:19unit.hold({ pack: "PK-1182", fastener: 7, reason: "torque trace off curve" })
  19. 08:05:19ok held at marriage · routed to rework · spec untouched
  20. 08:05:20sensors.fuse({ cams: 24, traces: true, tests: true })
  21. 13:40:00retest.sequence({ vehicles: 2, test: "ADAS calibration" })
  22. 13:52:31ok 2 retests passed inside takt
  23. 13:58:00mes.log_vehicle({ shift: 1, records: "as-built" })
  24. 14:00:05ok scenario complete · 10 steps · 0 escapes · shift released

Reasoning trace

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

GoalRun shift 1 on plant BIW-2 inside the qualified envelopes, hol…

Run shift 1 on plant BIW-2 inside the qualified envelopes, hold body geometry at the framing station, keep expulsion and paint defects from escaping, hold every torque to specification and prove every vehicle at end of line.

PlanSimulate weld-sequence, framing and booth candidates on the tw…

Simulate weld-sequence, framing and booth candidates on the twin first. Lead with stamping so panels arrive in dimension, then propose the weld schedule and hold it for a human, then correct framing inside the envelope, then set the booth ahead of the colour block. Fuse inspection continuously. Never touch a torque specification or a test verdict.

ThoughtThe standing weld schedule on W-14 runs current high enough to…

The standing weld schedule on W-14 runs current high enough to guarantee the joint on the thickest stack. With the new coil lot and panel dimension held at P-3, the twin predicts the same joint quality at 2 percent lower current with a 20 ms hold, and lower expulsion, because the panels arrive flatter.

Actiontwin.simulate(candidates=18) returns #6: blank feed +0.4 mm on…

twin.simulate(candidates=18) returns #6: blank feed +0.4 mm on P-3, weld current -2 percent and +20 ms hold on W-14, framing offset -0.3 mm at FS-1, booth B-2 humidity -2 points for the dark block.

ObservationCandidate #6 predicts geometry inside targets, expulsion risk …

Candidate #6 predicts geometry inside targets, expulsion risk 0.06, a lower dirt map and takt at 61 seconds. Three candidates scored better on takt but pushed predicted B-pillar variation past the tolerance edge and were discarded.

ActionExecute #6: six bounded writes permitted on stamping, framing,…

Execute #6: six bounded writes permitted on stamping, framing, booth, routing and sequencing; the weld-schedule write routed to the body-shop launch engineer; torque specifications and test limits locked.

ObservationDirt precursor in booth B-2 zone 3 at 07:40:02 before the humi…

Dirt precursor in booth B-2 zone 3 at 07:40:02 before the humidity trim took effect. Two defects localised and routed to spot repair; none escaped. One pack held at marriage on a torque trace at 08:05:19.

OutcomeScenario complete. Geometry inside targets, no expulsion escap…

Scenario complete. Geometry inside targets, no expulsion escapes, paint defects caught in station, one pack reworked, two ADAS retests passed inside takt. Shift 1 released with full as-built records.

Operations

Runbooks

What to do when.

Runbooks
SituationWhat happensWhat you do
Edge node offlineControl returns to the controller's last known-good state; safety PLCs and interlocks unaffectedCheck the node, restore, resume at the current autonomy level
Model version fails canaryAutomatic fallback to the previous validated version on that lineReview the evaluation record before re-promoting
Approval not answeredThe step waits; the run does not time out into a writeNamed approver or delegate decides in the console
Deadlock between agentsEscalates to a human rather than resolving by timeoutDecide in the console; the decision is logged
Rollback condition metThe tag returns to its previous valueReview the trigger signal and the run record
Attempt to write a locked tagRefused at the policy engine and again at the OT boundary; loggedReview which agent or policy requested it
Autonomy

Four levels, set per agent and per tag

A car plant does not go from manual to unattended in one step. Chassira 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 loops. Weld schedules stay supervised until the joint family is qualified, and torque specifications and test verdicts are never written by an agent.

Autonomy levels and the human role at each
LevelWhat the agent doesWhat the human doesWhere it sits in a pilot
L1 · ShadowReads weld, metrology, vision, torque, test, robot and MES signals; predicts and recommends; writes nothingRuns the line as today; compares predictions to audit and engineer outcomesDesign partners start here; the baseline is measured from the plant's own records
L2 · AssistProposes weld, framing, paint, routing, holding and sequencing moves with evidence, confidence, envelope and rollback pathApproves each action in the review consoleAssist mode: accuracy and ROI proven against the signed baseline
L3 · BoundedExecutes pre-approved low-risk actions: booth environment, framing offsets, blank feed and lubrication, routing, holds, sequencing, inside PLC and safety limits and the qualified envelopeApproves weld-schedule changes, torque-related decisions and vehicle releaseGraduated autonomy, after audited accuracy and ROI
L4 · ScaledSupervised weld-schedule adaptation for qualified joint families, across lines and plantsSets the envelope; reviews the shift record and evaluation resultsPlanned; after golden-dataset evaluation, twin validation and quality sign-off. Torque specifications and test verdicts never leave human hands
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.

chassira · cli · scenario
$ chassira run "shift 1 on BIW-2, program EV-CUV" --autonomy L2+

→ plan composed          10 steps · 1 approval gate
→ twin.simulate          18 candidates · best #6 · expulsion risk 0.06
→ policy.evaluate        6 writes permitted · weld_schedule held for human · torque_spec locked
→ executing              stamp.form ....... ok   continuous
! approval required      weld_schedule W-14 current −2% hold +20 ms
→ approved               body-shop launch engineer · 06:14:52
→ executing              weld.join ........ ok   continuous
→ executing              frame.geometry ... ok   continuous
→ executing              paint.finish ..... ok   continuous
! held                   pack PK-1182 · torque trace off curve · routed to rework
→ scenario complete      escapes 0 · shift 1 released

$ chassira runs show run_41a9c2 --format as-built
Limits

Platform limits and defaults

Design targets from the compute plan. None is a measured figure.

Platform limits and defaults
ItemDesign targetNotes
Edge inference, weld and gap-and-flush alertsunder 50 msJetson Orin at the cell, TensorRT
Edge inference, paint or dimensional anomaly promptsunder 150 msIncludes policy evaluation
Cameras per process area8 to 3215 to 60 FPS by task; DeepStream and Holoscan
Training and fine-tuning150 to 600 GPU-hours per plantDuring onboarding, then monthly incremental retraining; DGX or HGX planned
Synthetic images or variants50,000 to 250,000 per vehicle programCosmos and Omniverse Replicator, validated against real distributions; planned
Models served per plantRouted by latency, tenant and costTriton and NIM, versioned rollback, canary by line
Locked parametersTorque specs, joint parameters, test limits and verdictsNever writable, at any autonomy level
Guardrails

An agent near a crash-safety joint needs a leash

Chassira writes to production equipment. Every capability is scoped, every write is policy-checked against the qualified envelope, safety-critical parameters are locked, 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 and the qualified process envelope for the joint family, colour block or vehicle program.
  • Policy engine before every write. Autonomy level, shift, program, interlock state and operator presence are evaluated before a setpoint moves. NeMo Guardrails enforces spec, IATF, functional-safety, cyber and human-approval policy before any action writes back to robots, MES, QA or work instructions.
  • Safety-critical parameters locked. Weld schedules wait for a named body-shop engineer until the joint family is qualified. Torque specifications, battery-joint parameters and end-of-line test limits and verdicts are read-only to every agent, always.
  • Immutable audit log. Append-only and exportable. Every action records source evidence, the approved envelope, confidence, estimated quality, rework, downtime and warranty impact, rollback path, approver and vehicle scope.
  • Hard fallback. Loss of the edge node, the network or a model returns control to the press, robot, booth or MES controller's last known-good state. Safety-rated PLCs and interlocks are never in Chassira's path.
  • Tenant and program isolation. Vehicle designs, control plans, specs, models and memory never cross an OEM boundary. On-prem and plant-edge deployment are available for regulated plants.

Compliance posture

Compliance and certification status
ItemScopeStatus
SOC 2 Type ICloud control plane QUEUED Planned, first 6 months, with an IATF and functional-safety-aware review
SOC 2 Type IICloud control plane QUEUED Planned, 6 to 12 months
SSO and RBACConsole and approvals QUEUED Planned, 6 to 12 months
IATF 16949 and APQP assurance packagesDisposition and traceability evidence QUEUED Planned, 6 to 12 months; not a certification claim
ISO 26262-aware controlFunctional-safety requirements cited in reasoning and gates RUNNING In the design; not a certification claim
Standards-cited reasoningIATF 16949, APQP and PPAP, torque specs, recall procedures RUNNING In the design, every answer cites its source
Per-tenant and program isolationDesigns, control plans, models, memory RUNNING In the design from day one
On-prem and plant-edge deploymentRegulated OEM plants RUNNING Design option

Read the security overview

FAQ

Straight answers

The questions plant managers, launch engineers and quality 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 envelope, and only at the autonomy level your plant has set. Design partners start in shadow mode, where Chassira writes nothing. Weld-schedule changes wait for a named body-shop engineer, and torque specifications, battery-joint parameters and end-of-line test limits and verdicts are read-only to every agent, always.

Get started

Get documentation access

Documentation beyond this page opens with the design-partner cohort.