scenario

name: scenario description: Create and execute scenario YAML files for architecture what-if predictions. allowed-tools: - Read - Edit - Bash

scenario

Steps

1. Resolve the SAS empirical baseline first:
   • Use SAS architecture run metrics (derived_metrics.json -> P) from the relevant comparison batch.
   • If multiple SAS runs exist in the batch, pick one deterministic baseline and state which run id was used.
   • Do not use a hypothetical/model-predicted SAS point as the comparison baseline.
2. Collect model intelligence I, tool count, and candidate architectures.
3. Populate YAML with priors or explicit overrides, setting P_SA from the resolved SAS run baseline.
4. Run brainqub3 scenario run --scenario <path>.
5. Report scenario results relative to the SAS run baseline:
   • delta_vs_sas = P_architecture - P_SAS_run_baseline
6. Save comparison outputs for dashboard/report consumption.