Epic: Level 5 · Expert recipes #79

Recipes 53 to 60. Controlled optimization studies or closed-loop simulations requiring budgets, baselines, and held-out or trajectory evaluation.

Recipes (8)

• Recipe 53: Semantic feature discovery #53 Semantic feature discovery · Noul + Score · Evaluation & optimization
• Recipe 54: Question and policy optimization #54 Question and policy optimization · Choice + Noul + Score · Evaluation & optimization
• Recipe 55: Adaptive model routing #55 Adaptive model routing · Choice + Score · Evaluation & optimization
• Recipe 56: Adversarial harness evaluation #56 Adversarial harness evaluation · Noul · Trust & security
• Recipe 57: Evidence graph updates #57 Evidence graph updates · Choice + Noul · Data quality & knowledge graphs
• Recipe 58: Simulated process supervision #58 Simulated process supervision · Choice + Noul · Games & simulation
• Recipe 59: Observation and action selection #59 Observation and action selection · Choice · Games & simulation
• Recipe 60: Factory production control #60 Factory production control · Choice + Noul + Score · Games & simulation

Done when

• Every recipe above is merged and its issue closed
• The README catalog is regenerated (python tools/render_catalog.py) and shows these recipes as published
• CI is green on main
• A consistency pass across the level is done: section order, terminology, chart style, run-mode header

Dependencies

• Scheduled after Epic: Level 4 · Advanced recipes #78. A recipe here may start earlier once its own blockers are closed.
• Tracked in Cookbook roadmap: 60 recipes from foundation to release #80