A (IDS rows + factsheet) 14/24, B (factsheet only) 14/24,
C (no guards) 8/24. Factsheet delivers the recall lift; IDS rows
show no measurable effect. Evidence for dropping the guards
paragraph from MODEL_RENDER_PROFILES.md.
Both demos default to Fable; pass a model as the first arg (a.sh opus, sonnet,
haiku, or a full claude-... id) to override -- run both columns on the same
model for a fair A/B. Adds eval/ab token-savings scripts.