diff --git a/pilot/scene/chat_dashboard/prompt.py b/pilot/scene/chat_dashboard/prompt.py
index ae73c5825..b339d6334 100644
--- a/pilot/scene/chat_dashboard/prompt.py
+++ b/pilot/scene/chat_dashboard/prompt.py
@@ -23,10 +23,11 @@ According to the characteristics of the analyzed data, choose the most suitable
 {supported_chat_type}
 
 Pay attention to the length of the output content of the analysis result, do not exceed 4000tokens
+Do not use unprovided fields and field value in data analysis SQL, Do not use column pay_status as a query condition in  SQL.
+
 According to the characteristics of the analyzed data, choose the best one from the charts provided below to display, use different types of charts as much as possible，chart types:
 {supported_chat_type}
 
-Do not use unprovided fields and field value in data analysis SQL.
 Give {dialect} data analysis SQL, analysis title, display method and analytical thinking,respond in the following json format:
 {response}
 Ensure the response is correct json and can be parsed by Python json.loads
diff --git a/pilot/scene/chat_db/auto_execute/chat.py b/pilot/scene/chat_db/auto_execute/chat.py
index 9f5f919a2..8ed726a16 100644
--- a/pilot/scene/chat_db/auto_execute/chat.py
+++ b/pilot/scene/chat_db/auto_execute/chat.py
@@ -48,8 +48,8 @@ class ChatWithDbAutoExecute(BaseChat):
             "input": self.current_user_input,
             "top_k": str(self.top_k),
             "dialect": self.database.dialect,
-            "table_info": self.database.table_simple_info(self.db_connect)
-            # "table_info": client.get_similar_tables(dbname=self.db_name, query=self.current_user_input, topk=self.top_k)
+            # "table_info": self.database.table_simple_info(self.db_connect)
+            "table_info": client.get_similar_tables(dbname=self.db_name, query=self.current_user_input, topk=self.top_k)
         }
         return input_values