diff --git a/rdagent/components/coder/data_science/ensemble/prompts.yaml b/rdagent/components/coder/data_science/ensemble/prompts.yaml
index c9dacadd..544fcaab 100644
--- a/rdagent/components/coder/data_science/ensemble/prompts.yaml
+++ b/rdagent/components/coder/data_science/ensemble/prompts.yaml
@@ -90,7 +90,8 @@ ensemble_eval:
     {% endif %}
 
     ## Evaluation Criteria
-    You will be given the standard output (`stdout`) from the ensemble test and, if applicable, the workflow test.
+    - You will be given the standard output (`stdout`) from the ensemble test and, if applicable, the workflow test.
+    - Code should have no try-except blocks because they can hide errors.
     
     Please respond with your feedback in the following JSON format and order
     ```json
diff --git a/rdagent/components/coder/data_science/raw_data_loader/prompts.yaml b/rdagent/components/coder/data_science/raw_data_loader/prompts.yaml
index 2c88601d..b56ec586 100644
--- a/rdagent/components/coder/data_science/raw_data_loader/prompts.yaml
+++ b/rdagent/components/coder/data_science/raw_data_loader/prompts.yaml
@@ -329,6 +329,7 @@ data_loader_coder:
 
     ## Guidelines
     1. Ensure that the dataset is loaded strictly from `/kaggle/input/`, following the exact folder structure described in the **Data Folder Description**, and do not attempt to load data from the current directory (`./`).
+    3. You should avoid using logging module to output information in your generated code, and instead use the print() function.
 
     ## Output Format
     Please response the code in the following json format. Here is an example structure for the JSON output: