diff --git a/AI_Agents_Guide/Constrained_Decoding/README.md b/AI_Agents_Guide/Constrained_Decoding/README.md
index f2773500..82e2e00e 100644
--- a/AI_Agents_Guide/Constrained_Decoding/README.md
+++ b/AI_Agents_Guide/Constrained_Decoding/README.md
@@ -201,7 +201,7 @@ assistant
 
 ```
 
-## Enforcig Output Format via External Libraries
+## Enforcing Output Format via External Libraries
 
 In this section of the tutorial, we'll show how to impose constrains on LLMs,
 which are not inherently fine-tuned for constrained decoding. We'll
@@ -700,4 +700,4 @@ curl -X POST localhost:8000/v2/models/ensemble/generate -d '{"text_input": "Who
 This time, the expected response looks like:
 ```bash
 {"context_logits":0.0,...,"text_output":"Who is Harry Potter?{ \"name\": \"Harry Potter\",\"house\": \"Gryffindor\",\"blood_status\": \"Pure-blood\",\"occupation\": \"Wizards\",\"alive\": \"No\",\"wand\": {\"wood\": \"Holly\",\"core\": \"Phoenix feather\",\"length\": 11 }}"}
-```
\ No newline at end of file
+```