diff --git a/lotto/app/db.py b/lotto/app/db.py
index e840dde..32bae14 100644
--- a/lotto/app/db.py
+++ b/lotto/app/db.py
@@ -1039,36 +1039,40 @@ def bulk_insert_purchases_from_briefing(draw_no: int, tier_mode: str, amount: in
 # --- Lotto Briefings ---
 
 def save_briefing(data: Dict[str, Any]) -> int:
+    picks_json = json.dumps(data["picks"], ensure_ascii=False)
+    narrative_json = json.dumps(data["narrative"], ensure_ascii=False)
+    tier_rationale_json = json.dumps(data.get("tier_rationale") or {}, ensure_ascii=False)
     with _conn() as conn:
-        cur = conn.execute("""
+        cur = conn.execute(
+            """
             INSERT INTO lotto_briefings
                 (draw_no, picks, narrative, confidence, model,
                  tokens_input, tokens_output, cache_read, cache_write,
-                 latency_ms, source)
-            VALUES (?,?,?,?,?,?,?,?,?,?,?)
+                 latency_ms, source, tier_rationale)
+            VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
             ON CONFLICT(draw_no) DO UPDATE SET
-                picks=excluded.picks, narrative=excluded.narrative,
-                confidence=excluded.confidence, model=excluded.model,
+                picks=excluded.picks,
+                narrative=excluded.narrative,
+                confidence=excluded.confidence,
+                model=excluded.model,
                 tokens_input=excluded.tokens_input,
                 tokens_output=excluded.tokens_output,
                 cache_read=excluded.cache_read,
                 cache_write=excluded.cache_write,
                 latency_ms=excluded.latency_ms,
                 source=excluded.source,
+                tier_rationale=excluded.tier_rationale,
                 generated_at=datetime('now','localtime')
-        """, (
-            data["draw_no"],
-            json.dumps(data["picks"], ensure_ascii=False),
-            json.dumps(data["narrative"], ensure_ascii=False),
-            int(data["confidence"]),
-            data["model"],
-            int(data.get("tokens_input", 0)),
-            int(data.get("tokens_output", 0)),
-            int(data.get("cache_read", 0)),
-            int(data.get("cache_write", 0)),
-            int(data.get("latency_ms", 0)),
-            data.get("source", "auto"),
-        ))
+            """,
+            (
+                data["draw_no"], picks_json, narrative_json,
+                data["confidence"], data["model"],
+                data.get("tokens_input", 0), data.get("tokens_output", 0),
+                data.get("cache_read", 0), data.get("cache_write", 0),
+                data.get("latency_ms", 0), data.get("source", "auto"),
+                tier_rationale_json,
+            ),
+        )
         return cur.lastrowid
 
 
@@ -1078,6 +1082,7 @@ def _briefing_row(r) -> Dict[str, Any]:
         "draw_no": r["draw_no"],
         "picks": json.loads(r["picks"]),
         "narrative": json.loads(r["narrative"]),
+        "tier_rationale": json.loads(r["tier_rationale"]) if r["tier_rationale"] else {},
         "confidence": r["confidence"],
         "model": r["model"],
         "tokens_input": r["tokens_input"],
diff --git a/lotto/app/routers/briefing.py b/lotto/app/routers/briefing.py
index b4e0fb4..e6516b0 100644
--- a/lotto/app/routers/briefing.py
+++ b/lotto/app/routers/briefing.py
@@ -7,10 +7,24 @@ from .. import db
 router = APIRouter(prefix="/api/lotto")
 
 
+class TierRationale(BaseModel):
+    bonus: str = ""
+    extended: str = ""
+    pool: str = ""
+
+
+class BriefingPicks(BaseModel):
+    core: List[Dict[str, Any]] = Field(default_factory=list)
+    bonus: List[Dict[str, Any]] = Field(default_factory=list)
+    extended: List[Dict[str, Any]] = Field(default_factory=list)
+    pool: List[Dict[str, Any]] = Field(default_factory=list)
+
+
 class BriefingRequest(BaseModel):
     draw_no: int
-    picks: List[Dict[str, Any]]
+    picks: BriefingPicks
     narrative: Dict[str, Any]
+    tier_rationale: TierRationale = Field(default_factory=TierRationale)
     confidence: int = Field(ge=0, le=100)
     model: str
     tokens_input: int = 0
diff --git a/lotto/tests/test_briefing_4tier.py b/lotto/tests/test_briefing_4tier.py
new file mode 100644
index 0000000..b8761ef
--- /dev/null
+++ b/lotto/tests/test_briefing_4tier.py
@@ -0,0 +1,52 @@
+import sys, os
+sys.path.insert(0, os.path.dirname(os.path.dirname(__file__)))
+
+import pytest
+from app import db
+
+
+@pytest.fixture(autouse=True)
+def setup_db(tmp_path, monkeypatch):
+    test_db = tmp_path / "test.db"
+    monkeypatch.setattr(db, "DB_PATH", str(test_db))
+    db.init_db()
+    yield
+
+
+def test_save_briefing_4tier_roundtrip():
+    payload = {
+        "draw_no": 9999,
+        "picks": {"core":[{"numbers":[1,2,3,4,5,6],"risk_tag":"안정","reason":"x"}],
+                  "bonus":[], "extended":[], "pool":[]},
+        "narrative": {"headline":"H","summary_3lines":["a","b","c"],"retrospective":"r"},
+        "tier_rationale": {"bonus":"b1","extended":"e1","pool":"p1"},
+        "confidence": 70,
+        "model": "test",
+    }
+    bid = db.save_briefing(payload)
+    assert bid > 0
+    got = db.get_briefing(9999)
+    assert got["picks"]["core"][0]["numbers"] == [1,2,3,4,5,6]
+    assert got["tier_rationale"]["bonus"] == "b1"
+    assert got["narrative"]["retrospective"] == "r"
+
+
+def test_save_briefing_upsert_overwrites():
+    db.save_briefing({
+        "draw_no": 8888,
+        "picks": {"core":[], "bonus":[], "extended":[], "pool":[]},
+        "narrative": {"headline":"old","summary_3lines":["a","b","c"]},
+        "confidence": 50, "model": "v1",
+    })
+    db.save_briefing({
+        "draw_no": 8888,
+        "picks": {"core":[{"numbers":[10,20,30,40,41,42],"risk_tag":"공격","reason":"y"}],
+                  "bonus":[], "extended":[], "pool":[]},
+        "narrative": {"headline":"new","summary_3lines":["x","y","z"]},
+        "tier_rationale": {"bonus":"","extended":"","pool":""},
+        "confidence": 90, "model": "v2",
+    })
+    got = db.get_briefing(8888)
+    assert got["narrative"]["headline"] == "new"
+    assert got["confidence"] == 90
+    assert got["picks"]["core"][0]["risk_tag"] == "공격"