diff --git a/backend/app/services/doc_parser.py b/backend/app/services/doc_parser.py
index 3e5d0c2..fdf3606 100644
--- a/backend/app/services/doc_parser.py
+++ b/backend/app/services/doc_parser.py
@@ -297,7 +297,7 @@ STRUCTURAL ANALYSIS:
 IMPORTANT GUIDELINES:
 - Use the column mapping from the analysis to identify asset names, descriptions, tiers, and volumes
 - CRITICAL: If the document has tier columns (Tier A/B/C etc.), create a SEPARATE entry for EACH tier where volume > 0 or status = "Yes"
-- Example: "KV 360" with Tier A=No/0, Tier B=Yes/1, Tier C=Yes/1 → TWO entries: {name:"KV 360", tier:"Tier B", volume:1} and {name:"KV 360", tier:"Tier C", volume:1}
+- Example: "KV 360" with Tier A=No/0, Tier B=Yes/1, Tier C=Yes/1 → TWO entries: (name="KV 360", tier="Tier B", volume=1) and (name="KV 360", tier="Tier C", volume=1)
 - Do NOT create entries for tiers with volume=0 or status="No"
 - Skip rows that are questions, metadata, or caveats — those are not deliverables
 - Carry forward category names from merged cells (the analysis explains the hierarchy)