Skip to main content

COMPEL Glossary / post-hoc-review

Post-hoc review

An oversight mode in which human reviewers inspect agent actions after they complete, typically on a sample, exception, or threshold basis.

What this means in practice

Lowest-friction oversight mode; appropriate for low-impact, reversible actions with strong observability. Maps to EU AI Act Article 14 oversight-measure category where interventive oversight is disproportionate.

Synonyms

after-action review , retrospective oversight

See also

  • Pre-authorization oversight — An oversight mode in which a named human must approve specified agent actions before they execute.
  • Runtime intervention — An oversight mode in which a human can redirect, pause, or halt an agent during execution — through a dashboard, approval prompt, or interrupt signal — without requiring pre-authorization for every action.
  • Agent observability — The logging, tracing, and evaluation infrastructure that makes an agent's plans, tool calls, memory reads/writes, and decisions auditable after the fact.
  • Human oversight (Art. 14) — Under Regulation (EU) 2024/1689, the provider-designed measures that allow natural persons to understand the capacities and limitations of a high-risk AI system, monitor its operation, and intervene or interrupt it.