diff --git a/vision_agent/agent/vision_agent_prompts.py b/vision_agent/agent/vision_agent_prompts.py
index 6f0fdf74..4774d84d 100644
--- a/vision_agent/agent/vision_agent_prompts.py
+++ b/vision_agent/agent/vision_agent_prompts.py
@@ -15,7 +15,7 @@
 **Examples**:
 Here is an example of how you can interact with a user and Actions to complete a task:
 --- START EXAMPLES ---
-[Current directory: /workspace/test]
+[Current directory: /example/workspace]
 {examples}
 --- END EXAMPLES ---
 
@@ -27,16 +27,17 @@
 Here is the current conversation so far:
 --- START CONVERSATION ---
 [Current directory: {dir}]
+
 {conversation}
 """
 
 EXAMPLES_CODE1 = """
 USER: Can you detect the dogs in this image? Media name dog.jpg
 
-AGENT: {"thoughts": "I will use the generate_vision_code to detect the dogs in the image.", "response": "<execute_python>generate_vision_code('/workspace/test/dog_detector.py', 'Can you write code to detect dogs in this image?', media=['/workspace/test/dog.jpg'])</execute_python>", "let_user_respond": false}
+AGENT: {"thoughts": "I will use the generate_vision_code to detect the dogs in the image.", "response": "<execute_python>generate_vision_code('/example/workspace/dog_detector.py', 'Can you write code to detect dogs in this image?', media=['/example/workspace/dog.jpg'])</execute_python>", "let_user_respond": false}
 
 OBSERVATION:
-[File /workspace/test/dog_detector.py]
+[File /example/workspace/dog_detector.py]
 0|from vision_agent.tools import load_image, owl_v2
 1|def detect_dogs(image_path: str):
 2|    image = load_image(image_path)
@@ -44,7 +45,7 @@
 4|    return dogs
 [End of file]
 
-AGENT: {"thoughts": "I have generated the code to detect the dogs in the image, I must now run the code to get the output.", "response": "<execute_python>from dog_detector import detect_dogs\n    print(detect_dogs('/workspace/test/dog.jpg'))</execute_python>", "let_user_respond": false}
+AGENT: {"thoughts": "I have generated the code to detect the dogs in the image, I must now run the code to get the output.", "response": "<execute_python>from dog_detector import detect_dogs\n    print(detect_dogs('/example/workspace/dog.jpg'))</execute_python>", "let_user_respond": false}
 
 OBSERVATION:
 ----- stdout -----
@@ -55,10 +56,10 @@
 
 USER: The the image only has one dog, can you fix this?
 
-AGENT: {"thoughts": "I will use edit_vision_code to fix the code to detect only one dog. The lower score is 0.23 so I will set the threshold above that.", "response": "<execute_python>edit_vision_code('/workspace/test/dog_detector.py', ['Can you write code to detect dogs in this image?', 'Can you increase the threshold to 0.24?'], media=['/workspace/test/dog.jpg'])</execute_python>", "let_user_respond": false}
+AGENT: {"thoughts": "I will use edit_vision_code to fix the code to detect only one dog. The lower score is 0.23 so I will set the threshold above that.", "response": "<execute_python>edit_vision_code('/example/workspace/dog_detector.py', ['Can you write code to detect dogs in this image?', 'Can you increase the threshold to 0.24?'], media=['/example/workspace/dog.jpg'])</execute_python>", "let_user_respond": false}
 
 OBSERVATION:
-[File /workspace/test/dog_detector.py]
+[File /example/workspace/dog_detector.py]
 0|from vision_agent.tools import load_image, owl_v2
 1|def detect_dogs(image_path: str):
 2|    image = load_image(image_path)
@@ -66,7 +67,7 @@
 4|    return dogs
 [End of file]
 
-AGENT: {"thoughts": "I have edited the code to detect only one dog, I must now run the code to get the output.", "response": "<execute_python>from dog_detector import detect_dogs\n    print(detect_dogs('/workspace/test/dog.jpg'))</execute_python>", "let_user_respond": false}
+AGENT: {"thoughts": "I have edited the code to detect only one dog, I must now run the code to get the output.", "response": "<execute_python>from dog_detector import detect_dogs\n    print(detect_dogs('/example/workspace/dog.jpg'))</execute_python>", "let_user_respond": false}
 
 OBSERVATION:
 ----- stdout -----
@@ -82,10 +83,10 @@
 
 USER: Yes you can use workers.png
 
-AGENT: {"thoughts": "I will use the generate_vision_code to count the workers with helmets in the image.", "response": "<execute_python>generate_vision_code('/workspace/test/code.py', 'Can you write code to count workers with helmets in this image?', media=['/workspace/test/workers.png'])</execute_python>", "let_user_respond": false}
+AGENT: {"thoughts": "I will use the generate_vision_code to count the workers with helmets in the image.", "response": "<execute_python>generate_vision_code('/example/workspace/code.py', 'Can you write code to count workers with helmets in this image?', media=['/example/workspace/workers.png'])</execute_python>", "let_user_respond": false}
 
 OBSERVATION:
-[File /workspace/test/code.py]
+[File /example/workspace/code.py]
 0|from vision_agent.tools import load_image, owl_v2, closest_box_distance
 1|def count_workers_with_helmets(image_path: str):
 2|    image = load_image(image_path)
@@ -104,7 +105,7 @@
 15|    return count
 [End of file]
 
-AGENT: {"thoughts": "I have generated the code to count the workers with helmets in the image, I must now run the code to get the output.", "response": "<execute_python>from code import count_workers_with_helmets\n    print(count_workers_with_helmets('/workspace/test/workers.png'))</execute_python>", "let_user_respond": false}
+AGENT: {"thoughts": "I have generated the code to count the workers with helmets in the image, I must now run the code to get the output.", "response": "<execute_python>from code import count_workers_with_helmets\n    print(count_workers_with_helmets('/example/workspace/workers.png'))</execute_python>", "let_user_respond": false}
 
 OBSERVATION:
 ----- stdout -----