Public report sample. Retained results from one dairy delivery, with local paths and source files omitted. Read the explanation.

Dairy plant - caller-mapped acceptance brief

Needs review · Next action: Review finding

Acceptance of the delivered OpenUSD scene against the owner brief, with explicit agent tolerances

2,081 prims, 1,105 meshes, 158 materials

137Passed check rows
0Failed check rows
7Unresolved declared requirements
10AI-routed human-review items

These categories overlap and use different units. Review items are not a count of defects or assets.

What needs attention

What was considered

Input or stageIncluded statusContext
Brief providedYesDairy plant - caller-mapped acceptance brief · Requirements and sources
Brief provenanceMap authored by the producing agent from the owner-supplied brief; tolerances are agent decisions.Recorded authorship; not independently authenticated.
Brief source files1 textText and reference images describe the requested result.
Brief interpretation reviewpendingProducer-authored map; relevance and tolerances need owner review
Scene dataSaved USD inspecteddairy_plant.usda
Scripted checksCompletedbrief.measurements, materials, motion.connection, nvidia.asset-validator, openusd, scene.audit, textures.decode
Rendered views supplied0 recorded viewsSupplied does not mean eligible for every review question.
Visual evidence and judgeNot requestedCaller-supplied views are separate from reference images in a brief.
Text context for triage2 selected text sourcesSee exactly what was considered
Producer decisions recorded0Only declared decisions in this assessment are counted.
Undeclared-assumption auditNo audit record attachedThis report does not establish whether another audit ran.
AI useText triage onlyModel opinions do not replace measurements or human decisions.

Check results

BasisChecksPassWarningFailUnknownErrorNo subjects
General structural and delivery checks272300004
Checks linked to human specifications11411400000

Inspect every check, its subjects and measurements. Subject counts are kept per check and never summed into a unique-asset total.

AI risk triage

ExecutionSelected itemsLowMediumHighUnratedMore contextRoutine
Completed14460031

Low, medium and high prioritize human review; they are not verified engineering risk. Reasons, policy overrides and evidence.