diff --git a/agents/rag/setup_corpus.py b/agents/rag/setup_corpus.py
index 7998f32..7142201 100644
--- a/agents/rag/setup_corpus.py
+++ b/agents/rag/setup_corpus.py
@@ -3,12 +3,12 @@
 setup_corpus.py — Create a Vertex AI RAG Engine corpus and import documents.
 Project: propane-will-491900-m5
 
-Explicitly uses Serverless (RagManagedDb basic tier) to avoid
-Spanner allowlist restrictions on new projects in us-central1.
+Explicitly uses Serverless (RagManagedDb) to avoid Spanner allowlist
+restrictions on new projects in us-central1.
 
 Tested against vertexai SDK 1.153.1:
-  RagVectorDbConfig(vector_db=RagManagedDb(tier=1))
-  tier=1 == BASIC (serverless), tier=2 == ENTERPRISE
+  RagVectorDbConfig(vector_db=RagManagedDb())
+  RagManagedDb is a no-arg marker class — selecting it is sufficient for serverless.
 """
 
 import os
@@ -27,9 +27,6 @@ GCS_SOURCE = os.environ.get(
     f"gs://{PROJECT_ID}-agent-staging/rag-docs/",
 )
 
-# tier=1 == BASIC (serverless), tier=2 == ENTERPRISE
-_TIER_BASIC = 1
-
 
 def ensure_serverless_engine_config() -> None:
     """
@@ -83,10 +80,10 @@ def get_or_create_corpus() -> RagCorpus:
     print(f"Creating corpus '{CORPUS_DISPLAY_NAME}' in {LOCATION} (serverless)...")
     corpus = rag.create_corpus(
         display_name=CORPUS_DISPLAY_NAME,
+        # RagManagedDb() is a no-arg marker class in SDK 1.153.1
+        # Selecting it routes to serverless managed DB (basic tier)
         backend_config=rag.RagVectorDbConfig(
-            vector_db=rag.RagManagedDb(
-                tier=_TIER_BASIC,  # 1 = BASIC (serverless)
-            )
+            vector_db=rag.RagManagedDb()
         ),
     )
     print(f"✓ Corpus created: {corpus.name}")