Skip to content
Human Intelligence seal
Human Intelligence
§ I · Domain SPC · Control 7 of 9
Control
SPC-07
Edition
v.1.3
Status
Public review

SPC · Agent Specification & Pre-Deployment Assurance

SPC-07Versioned evaluation set

A versioned evaluation set is maintained per agent and re-executed on every material change. Results are retained as evidence.

Each agent has a versioned evaluation set that is maintained alongside the agent's specification. The evaluation set is re-executed on every material change, and results are retained as evidence. The evaluation set evolves as new failure modes are discovered, ensuring that previously identified risks remain covered.

Table SPC-07.1 · Maturity criteria · v.1.3

L1 to L5 · the lowest level in scope caps the agent
L1Ad hoc

Controls exist informally; documentation is incomplete; no consistent review.

L2Documented

Controls are written down; ownership is assigned; review cadence is defined.

L3Operated

Controls are followed in practice; evidence is collected; deviations are tracked.

Evaluation set is version-controlled; execution history shows re-runs on material changes; results are retained and accessible for audit; the set has been updated to cover newly discovered failure modes.

L4Measured

Control effectiveness is measured against documented thresholds; trends are reported.

L5Continuously Improved

Controls evolve based on incident learning; maturity gains are evidenced over time.

The v1.3 edition publishes a control-specific criterion at L3 (Operated). The other levels apply the general ladder to this control; see the maturity ladder.

Evidence an assessor asks for

  1. E.1

    Evaluation set is version-controlled.

  2. E.2

    Execution history shows re-runs on material changes.

  3. E.3

    Results are retained and accessible for audit.

  4. E.4

    The set has been updated to cover newly discovered failure modes.

Table SPC-07.2 · Framework mappings

5 of 7 frameworks carry a control-level reference
NIST AI RMFMANAGE 3.1, MANAGE 3.2NIST AI Risk Management Framework 1.0
ISO/IEC 42001A.6.2.6ISO/IEC 42001:2023 · Artificial intelligence management system
OWASP LLM Top 10·OWASP Top 10 for Large Language Model Applications
SOC 2 (TSC)CC8.1, CC8.2AICPA Trust Services Criteria for SOC 2 Type II
EU AI ActArt. 9(7)EU AI Act · Regulation (EU) 2024/1689
MITRE ATLAS·MITRE ATLAS · Adversarial Threat Landscape for AI Systems
SingaporeMAIGF Testing & Assurance, AI Verify ReproducibilitySingapore Model AI Governance Framework / AI Verify / PDPA

Mappings are directional: meeting this control evidences but does not by itself satisfy the external requirement. A middle dot means no control-level reference is published at this edition; see the crosswalk.

Related controls and terms

Cite this control

Human Intelligence. HI-AAF v1.3, SPC-07 Versioned evaluation set. Public review edition, July 2026. https://humanintel.net/standard/spc/spc-07

Edition v.1.3 · July 2026 · Public review · Markdown · PDF

https://humanintel.net/standard/spc/spc-07

Notice

HI-AAF v1.3 is an independent framework published by Human Intelligence. It is not affiliated with NIST, ISO, AICPA, or any government or accreditation body. The framework is offered openly for review during the current draft cycle.