Handbook

L3.4 — Multiple slices under one campaign

Status: Defined

Updated

Sub-level at a glance
Parent level L3 — Use-case slice
Autonomous unit Multiple slices under one campaign
Distinct assay evidence ≥2 L3.x-passing items under one campaign id
Grade today a

Canonical policy, grades a-d, and promotion criteria: Autonomy levels (Blueprints). Per-project scoring: Autonomy maturity framework (Blueprints).

Gates and evidence

All gates and core evidence of the parent level (L3 — Use-case slice) apply unchanged. Declaring this sub-level adds the distinct check:

  • ≥2 campaign items, each individually passing an L3.x assay, recorded under one campaign id

A run that fails the sub-level check may still be reported at the plain parent-level grain if the parent's evidence holds — sub-level claims are strictly additive.

Prompt pack

Execution rubric (repo path, nav-hidden): prompts/autonomy/sublevel-l3-4.md — workcell-skeleton prompt declaring this sub-level, its evidence-to-return shape, and human gates.

Worked case

Hypothetical case — no campaign has recorded ≥2 L3.x-passing items under one id yet.

Field Value
Repo forge-dark-factory PoC (hypothetical multi-item campaign)
Goal Two independent L3.x slices (L3-ui-smoke + L3-scan-flow) under campaign lenses-production-l3-multi
Evidence produced Pattern: runs/campaigns/lenses-production-l3-multi/{item-a,item-b}/run-*/machine/assay.json each ok: true at L3.x
Assay pass rationale L3.4 _check_sublevel: campaign_passing_items >= 2 — each item individually passes its L3.x sub-level assay
Assay fail example Only one green L3.x item → L3.4 evidence: need >=2 L3.x-passing campaign items, got 1