diff --git a/docs/reports/Viewclinic_QB_Results_TOP50.xlsx b/docs/reports/Viewclinic_QB_Results_TOP50.xlsx
index 8068109..122102c 100644
Binary files a/docs/reports/Viewclinic_QB_Results_TOP50.xlsx and b/docs/reports/Viewclinic_QB_Results_TOP50.xlsx differ
diff --git a/scripts/export_qb_excel.py b/scripts/export_qb_excel.py
index b312dad..6de142f 100644
--- a/scripts/export_qb_excel.py
+++ b/scripts/export_qb_excel.py
@@ -194,11 +194,14 @@ def main():
         ws.column_dimensions[col].width = w
 
     # ── 엔진별 상세 (답변 전문 + 인용) ────────────────────
+    # 논브랜드 84문항만 수록 (브랜드 직접 질문 36개의 원본 답변은 scripts/out/ JSONL 참조)
     for sheet, data in (("GPT상세", oa), ("PPLX상세", px)):
         ws = wb.create_sheet(sheet)
-        ws.append(["ID", "질문", "뷰 언급", "순위", "답변 전문", "인용 URL"])
+        ws.append(["ID", "질문 (논브랜드 84문항)", "뷰 언급", "순위", "답변 전문", "인용 URL"])
         style_header(ws, 6)
         for q in qs:
+            if brand(q):
+                continue
             r = data[q["id"]]
             ws.append([q["id"], q["question"],
                        "O" if r.get("view_mentioned") else "X", r.get("view_rank") or "",