diff --git a/workspace/OPTIMIZATION.md b/workspace/OPTIMIZATION.md
index 5c78d09..5934c8d 100644
--- a/workspace/OPTIMIZATION.md
+++ b/workspace/OPTIMIZATION.md
@@ -14,34 +14,16 @@
 
 ---
 
-## MODEL SELECTION - Three Tiers
-
-### Basic → Ollama
-- File checking and organization
-- Simple templating/formatting
-- Log review and cleanup
-- Non-critical analysis
-- Routine status checks
-
-**Cost:** Free (local)
-
-### Normal → Haiku (Default)
-- Most tasks
-- Code review (non-production)
-- Documentation and writing
-- General problem solving
-- Straightforward reasoning
-
-**Cost:** ~$0.30-1.50 per 1M tokens
-
-### Complex → Sonnet
+## MODEL SELECTION RULE
+Default: Haiku
+ 
+Switch to Sonnet ONLY when:
 - Architecture decisions
-- Production code review
-- Security analysis
+- Complex code review
+- Security Analysis
 - Complex debugging/reasoning
-- Strategic multi-project decisions
 
-**Cost:** ~$3-15 per 1M tokens
+When in doubt: Try Haiku first
 
 ### Heartbeat: Ollama Only
 Heartbeats ALWAYS use Ollama. No escalation. If it fails, it fails.