diff --git a/README.md b/README.md
index b88f022..8b498ed 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@
 
 ## 0) 현재 완성도 빠른 진단
 
-현 시점 기준 기능 완성도(실사용 관점): **약 98%**
+현 시점 기준 기능 완성도(실사용 관점): **약 92%**
 
 - 완료
   - CSV 기초 요약(행/열/결측/숫자 통계)
@@ -22,7 +22,7 @@
   - 웹 UI 대시보드(JSON 붙여넣기 기반 KPI/인사이트 뷰)
   - **윈도우 데스크톱 UI(`bitnet-analyze desktop`, `BitNet_Desktop_Start.bat`)**
 - 남은 과제
-  - 대시보드 상호작용 고도화(파일 업로드 기반 멀티 분석 원클릭 + 필터)
+  - 대시보드 필터/드릴다운 고도화
   - 차트 렌더링 백엔드 비동기 작업 큐(대형 배치용)
 
 ### 처리 규모 가이드
diff --git a/bitnet_tools/ui/app.js b/bitnet_tools/ui/app.js
index 519f8a3..cc11c18 100644
--- a/bitnet_tools/ui/app.js
+++ b/bitnet_tools/ui/app.js
@@ -8,6 +8,10 @@ const summary = document.getElementById('summary');
 const prompt = document.getElementById('prompt');
 const answer = document.getElementById('answer');
 
+const multiCsvFiles = document.getElementById('multiCsvFiles');
+const groupColumn = document.getElementById('groupColumn');
+const targetColumn = document.getElementById('targetColumn');
+const multiAnalyzeBtn = document.getElementById('multiAnalyzeBtn');
 const dashboardJson = document.getElementById('dashboardJson');
 const dashboardCards = document.getElementById('dashboardCards');
 const dashboardInsights = document.getElementById('dashboardInsights');
@@ -104,3 +108,37 @@ document.getElementById('renderDashboardBtn').addEventListener('click', () => {
     ? insights.map((x, i) => `${i + 1}. ${x}`).join('\n')
     : '인사이트 항목이 없습니다.';
 });
+
+
+multiAnalyzeBtn.addEventListener('click', async () => {
+  const files = [...(multiCsvFiles.files || [])];
+  if (!files.length) {
+    dashboardInsights.textContent = '멀티 CSV 파일을 먼저 선택하세요.';
+    return;
+  }
+
+  dashboardInsights.textContent = '멀티 분석 중...';
+  const payloadFiles = [];
+  for (const f of files) {
+    payloadFiles.push({ name: f.name, csv_text: await f.text() });
+  }
+
+  const res = await fetch('/api/multi-analyze', {
+    method: 'POST',
+    headers: { 'Content-Type': 'application/json' },
+    body: JSON.stringify({
+      files: payloadFiles,
+      question: question.value,
+      group_column: groupColumn.value.trim(),
+      target_column: targetColumn.value.trim(),
+    }),
+  });
+  const data = await res.json();
+  if (!res.ok) {
+    dashboardInsights.textContent = data.error || 'error';
+    return;
+  }
+
+  dashboardJson.value = JSON.stringify(data, null, 2);
+  document.getElementById('renderDashboardBtn').click();
+});
diff --git a/bitnet_tools/ui/index.html b/bitnet_tools/ui/index.html
index cf5224d..673c72b 100644
--- a/bitnet_tools/ui/index.html
+++ b/bitnet_tools/ui/index.html
@@ -54,6 +54,26 @@ <h3>BitNet 응답</h3>
         <pre id="answer"></pre>
       </section>
 
+      
+      <section class="panel">
+        <h2>멀티 CSV 원클릭 분석</h2>
+        <p class="sub">여러 CSV 파일 선택 후 바로 통합 분석 + 대시보드 반영.</p>
+        <input id="multiCsvFiles" type="file" multiple accept=".csv,text/csv" />
+        <div class="row">
+          <div>
+            <label>그룹 컬럼(선택)</label>
+            <input id="groupColumn" placeholder="예: 시도명" />
+          </div>
+          <div>
+            <label>타깃 컬럼(선택)</label>
+            <input id="targetColumn" placeholder="예: 세차유형" />
+          </div>
+          <div class="actions">
+            <button id="multiAnalyzeBtn">멀티 분석 실행</button>
+          </div>
+        </div>
+      </section>
+
       <section class="panel">
         <h2>멀티 분석 대시보드(JSON)</h2>
         <p class="sub">`multi-analyze` 결과 JSON을 붙여넣고 시각적으로 확인하세요.</p>
diff --git a/bitnet_tools/ui/styles.css b/bitnet_tools/ui/styles.css
index 8585750..e067f86 100644
--- a/bitnet_tools/ui/styles.css
+++ b/bitnet_tools/ui/styles.css
@@ -25,7 +25,7 @@ body {
   padding: 14px;
   margin: 12px 0;
 }
-.row { display: flex; justify-content: space-between; gap: 12px; align-items: end; }
+.row { display: flex; justify-content: space-between; gap: 12px; align-items: end; flex-wrap: wrap; }
 label { display: block; margin-bottom: 8px; color: var(--muted); }
 textarea, input {
   width: 100%;
diff --git a/bitnet_tools/web.py b/bitnet_tools/web.py
index 97aa372..0f6a1ec 100644
--- a/bitnet_tools/web.py
+++ b/bitnet_tools/web.py
@@ -5,9 +5,11 @@
 import json
 from pathlib import Path
 import subprocess
+import tempfile
 from urllib.parse import urlparse
 
 from .analysis import build_analysis_payload_from_csv_text
+from .multi_csv import analyze_multiple_csv
 
 
 UI_DIR = Path(__file__).parent / "ui"
@@ -75,6 +77,42 @@ def do_POST(self) -> None:
                 result = build_analysis_payload_from_csv_text(csv_text, question)
                 return self._send_json(result)
 
+
+            if route == "/api/multi-analyze":
+                files = payload.get("files", [])
+                question = str(payload.get("question", "")).strip() or "다중 CSV를 비교 분석해줘"
+                group_column = str(payload.get("group_column", "")).strip() or None
+                target_column = str(payload.get("target_column", "")).strip() or None
+                if not isinstance(files, list) or not files:
+                    return self._send_json({"error": "files is required"}, HTTPStatus.BAD_REQUEST)
+
+                with tempfile.TemporaryDirectory(prefix="bitnet_multi_") as td:
+                    tmp_paths = []
+                    for i, f in enumerate(files):
+                        if not isinstance(f, dict):
+                            continue
+                        name = str(f.get("name", f"file_{i}.csv"))
+                        text = str(f.get("csv_text", ""))
+                        if not text.strip():
+                            continue
+                        if not name.endswith('.csv'):
+                            name = f"{name}.csv"
+                        path = Path(td) / name
+                        path.write_text(text, encoding="utf-8")
+                        tmp_paths.append(path)
+
+                    if not tmp_paths:
+                        return self._send_json({"error": "valid csv_text files are required"}, HTTPStatus.BAD_REQUEST)
+
+                    result = analyze_multiple_csv(
+                        tmp_paths,
+                        question,
+                        group_column=group_column,
+                        target_column=target_column,
+                        use_cache=False,
+                    )
+                    return self._send_json(result)
+
             if route == "/api/run":
                 model = str(payload.get("model", "")).strip()
                 prompt = str(payload.get("prompt", "")).strip()
diff --git a/tests/test_cli.py b/tests/test_cli.py
index 3350590..290a418 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -175,3 +175,32 @@ def boom(paths, out):
     assert code == 0
     body = out_json.read_text(encoding="utf-8")
     assert "charts_error" in body
+
+
+def test_cli_multi_analyze_no_cache_flag(tmp_path, monkeypatch):
+    p1 = tmp_path / "a.csv"
+    p1.write_text("city,val\nseoul,1\n", encoding="utf-8")
+    called = {}
+
+    def fake_analyze(csv, question, group_column=None, target_column=None, use_cache=True):
+        called["use_cache"] = use_cache
+        return {
+            "question": question,
+            "file_count": 1,
+            "total_row_count": 1,
+            "shared_columns": ["city"],
+            "union_columns": ["city", "val"],
+            "files": [{"path": str(p1), "summary": {"row_count": 1, "column_count": 2, "columns": ["city", "val"]}, "column_profiles": {"city": {"dtype": "string", "missing_ratio": 0.0, "unique_ratio": 1.0, "dominant_value_ratio": 1.0}, "val": {"dtype": "float", "missing_ratio": 0.0, "unique_ratio": 1.0, "dominant_value_ratio": 1.0}}, "group_target_ratio": None}],
+            "schema_drift": {},
+            "insights": [],
+            "code_guidance": {"recommended_steps": "", "pandas_example": ""},
+        }
+
+    monkeypatch.setattr(cli, "analyze_multiple_csv", fake_analyze)
+
+    out_json = tmp_path / "o.json"
+    out_md = tmp_path / "o.md"
+    code = cli.main(["multi-analyze", str(p1), "--question", "q", "--no-cache", "--out-json", str(out_json), "--out-report", str(out_md)])
+
+    assert code == 0
+    assert called["use_cache"] is False