diff --git a/docs/source/en/main_classes/agent.md b/docs/source/en/main_classes/agent.md
index fe483d6dde9e60..e5d4f629b0a875 100644
--- a/docs/source/en/main_classes/agent.md
+++ b/docs/source/en/main_classes/agent.md
@@ -87,6 +87,7 @@ These engines have the following specification:
 ### HfEngine
 
 For convenience, we have added a `HfEngine` that implements this and uses an inference endpoint for the execution of the LLM.
+It accepts an argument `stop_sequences` to stop it in its generation, which will be helpful for controlling our LLM engine's output.
 
 ```python
 >>> from transformers import HfEngine
@@ -94,12 +95,12 @@ For convenience, we have added a `HfEngine` that implements this and uses an inf
 >>> messages = [
 ...   {"role": "user", "content": "Hello, how are you?"},
 ...   {"role": "assistant", "content": "I'm doing great. How can I help you today?"},
-...   {"role": "user", "content": "I'd like to show off how chat templating works!"},
+...   {"role": "user", "content": "No need to help, take it easy."},
 ... ]
 
->>> HfEngine()(messages)
+>>> HfEngine()(messages, stop_sequences=["conversation"])
 
-"That sounds like a lot of fun! I'd be happy to help you demonstrate chat templating. Please go ahead and show me how it works."
+"That's very kind of you to say! It's always nice to have a relaxed "
 ```
 
 [[autodoc]] HfEngine