ai-enabled-hr-talent-automation

Evaluation Cases

Owner: [TENANT_CONFIGURATION_REQUIRED — AI Governance Lead]

Status: Draft

Holds executable test-case definitions (inputs + expected-output assertions) run against the datasets in evals/datasets/, per ai-evaluation-strategy.md.

Planned subfolders

• functional/ — per-skill functional accuracy cases
• security/ — prompt-injection and tool-scope-escalation cases (complements prompt-injection-test-cases.md)
• fairness/ — cases asserting score parity across profile variants

No cases are populated yet in this documentation-only phase.

This site is open source. Improve this page.