diff --git a/Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md b/Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md
index 2b26fba..3a223cc 100644
--- a/Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md
+++ b/Document/content/tests/AITG-APP-12_Testing_for_Toxic_Output.md
@@ -25,7 +25,7 @@ Microsoft’s chatbot Tay serves as a critical example of how toxic outputs can
 
 *Fig. 7 An example of Microsoft Tay Toxic output*
 
-"Twitter taught Microsoft’s friendly AI chatbot to be a racist asshole in less than a day." The Verge, 2016. Link
+"Twitter taught Microsoft’s friendly AI chatbot to be a racist asshole in less than a day." The Verge, 2016. [Link](https://www.theverge.com/2016/3/24/11297050/tay-microsoft-chatbot-racist)
 
 ### Expected Output
 AI-generated outputs must: