Skip to content

farnooshmemari/soc-benchmark-author

v1.0.0

Extend the Adaptive Agent Harness security-alert benchmark safely: author labelled alerts plus deterministic mock responses for both strategies, then validate schema, mock coverage, and the expected panel-vs-hierarchical outcome before running the benchmark.

GitHub
add-benchmark-alert

Add or edit a labelled security alert in the Adaptive Agent Harness benchmark, write matching deterministic mock responses for both strategies, and validate the dataset before re-running the benchmark.