diff --git a/Labs/Exercise-04.md b/Labs/Exercise-04.md
index 408fadb..eb7ba20 100644
--- a/Labs/Exercise-04.md
+++ b/Labs/Exercise-04.md
@@ -162,7 +162,8 @@ It involves analyzing and refining workflow processes to ensure maximum efficien
 
     ![](./media/image-43.png)
    
-1. After the batch run and evaluation run complete, in the run detail page, multi-select the batch runs for each variant, then select Visualize outputs. You will see the metrics of 2 variants for the classify_with_llm node and LLM predicted outputs for each record of data.
+1. After the batch run and evaluation run complete, in the run detail page, multi-select the batch runs for each variant, then select Visualize outputs. You will be able to see the metrics of 2 variants for the 
+   classify_with_llm node and LLM, along with predicted outputs for each recorded data. 
 
 1. After you identify which variant is the best, you can go back to the flow authoring page and set that variant as default variant of the node