PUBLIC SYNTHETIC EXAMPLE — no real participant or pilot. The private label below describes the report default, not a confidentiality claim about this constructed example.
Evidence supports a bounded engineering step
PRIVATE working record; review permission and identifying content before sharing.
SYNTHETIC-LOW-001 · Fictional advisor intake · 0.1-rc.4-candidate.3
Engineering recommendation only. Owner authorization and deployment evaluation are separate.
| Decision | Profile needed | Risk | First stop |
|---|---|---|---|
| PROCEED_TO_ENGINEERING | QUICK6 | low | No gate stop |
Machine checks: structure and decision rules only. Human evidence-quality review: RECORDED_PASS. Evidence authenticity is not independently verified; no criterion certification is issued.
Do next
Does the named owner authorize this exact bounded engineering step?
Owner: engineering lead. Record the owner's separate dated authorization or refusal and conditions. Do not infer authorization from a gate pass.
Six gates - no combined score
| Gate and criteria | Result | What is missing or failed |
|---|---|---|
| Understand today's work (HCAI-1.2) | PASS | Required checks passed |
| Name the need and success condition (HCAI-1.1, HCAI-1.3, HCAI-1.4) | PASS | Required checks passed |
| Walk through normal work, failure and recovery (HCAI-3.1, HCAI-3.2) | PASS | Required checks passed |
| Inspect why each artifact belongs (HCAI-2.1, HCAI-2.2, HCAI-2.3) | PASS | Required checks passed |
| Count the work AI leaves or creates (HCAI-3.3) | PASS | Required checks passed |
| Bound the engineering decision (HCAI-4.1, HCAI-4.2, HCAI-4.3, HCAI-4.4, HCAI-4.5) | PASS | Required checks passed |
PASS means the structural rules and supplied review judgments satisfy this gate. It does not prove the evidence is true or sufficient in practice. MISSING means gather evidence; FAIL means repair a known problem; NOT_EVALUATED means no conclusion was drawn.
Keep these results separate
| Result | Value | Interpretation |
|---|---|---|
| Gross labor minutes saved / case | 15.0 | Before AI-output oversight |
| Oversight minutes / case | 5.0 | Review + correction + escalation + rework |
| Net labor minutes saved / case | 10.0 | Projected; not measured performance |
| Net operating benefit / period | 470.0 | USD / month; PROJECTED |
| Preparation elapsed minutes | 0.0 | Outside the short session, never hidden |
| Review session elapsed minutes | 12.0 | Includes capture/reporting |
| Total evaluation person-minutes | 24.0 | Disjoint preparation + evaluator + participant + adjudication |
| Protocol evaluation cost | 12.0 | USD |
| Operational system performance | not_collected | No deployment decision is made by this instrument |
Missing values are not zero. Money and time are scenario estimates unless separately observed. Evaluation expense is not workflow operating cost.
Current workflow - observed versus reported
| Step | Role and action | Next / endpoint | Basis |
|---|---|---|---|
| C1 | intake advisor: Read and check intake | C2, C4 | observed |
| C2 | intake advisor: Ask for correction | C3 | reported |
| C3 | intake advisor: Correct saved fields or retain cancelled record | C4 | reported |
| C4 | intake lead: Confirm or close intake | Endpoint | observed |
People and consequences
Affected roles: intake advisor, requester
| Review area | Applicability and reason | Requirements / owner |
|---|---|---|
| access_usability | applicable: Stipulated synthetic case: readable editable drafts, equal correction access, local fictional data, advisor control. Not empirical evidence. | R1 / intake lead |
| privacy_security | applicable: Stipulated synthetic case: readable editable drafts, equal correction access, local fictional data, advisor control. Not empirical evidence. | R1 / intake lead |
| unequal_effects | applicable: Stipulated synthetic case: readable editable drafts, equal correction access, local fictional data, advisor control. Not empirical evidence. | R1 / intake lead |
| human_agency | applicable: Stipulated synthetic case: readable editable drafts, equal correction access, local fictional data, advisor control. Not empirical evidence. | R1 / intake lead |
Proposed workflow - connected paths
| State | Behavior | Next / endpoint |
|---|---|---|
| S1 | Review request | S2, S4 |
| S2 | Flag missing field | S3 |
| S3 | Retain corrected or cancelled intake | S4 |
| S4 | Close with retained record | Endpoint |
Inspect requirement -> artifact -> check
R1: Correct or cancel without data loss
Success condition: All three paths preserve the defined fields
Behavior shown: simulated; this label is not inferred from visual fidelity.
Form: Review form with editable fields | Fit: Advisor intake workflow and email dependency | Function: Preserve details through correction/cancel
Reference records: E1
Artifact E1 · version fixture-1 · SHA-256 87a35fd15180404eedfd92f7c23b7afc6e35d8309ff1af4581ec356baaf2a5c7
Check T1: Stipulated three-path walkthrough | walkthrough | pass | tested revision matches: True | requirement/context matches: True
Bounded owner decision
Owner: engineering lead
Engineering step: Build a disposable intake prototype
Resource cap: One engineer-day; no live sending
Revisit trigger: Review after prototype walkthrough
Owner authorization: pending separate dated record. A recommendation alone does not permit deployment.
Provenance and limits
Versions: protocol 0.1-rc.4-candidate.3; mcp 0.2.0rc3; skill 0.2.0-rc.3; contract 0.2.0-rc.3
Input SHA-256: 8dbffb0eb3e7f6c6ea23eb3cb820b9a32befdaaaa3539335db89a9d568cbbf9e
Previous run: Not recorded; revision: Not recorded
Evidence digests are supplied and structurally checked, not independently fetched or authenticated. Practitioner correspondence and software tests do not establish empirical effectiveness.