diff --git a/playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent.py b/playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent.py
new file mode 100644
index 000000000..f54628471
--- /dev/null
+++ b/playground/demos/multi_modal_autonomous_agents/multi_modal_auto_agent.py
@@ -0,0 +1,17 @@
+from swarms.structs import Flow
+from swarms.models.gpt4_vision_api import GPT4VisionAPI
+
+
+llm = GPT4VisionAPI()
+
+task = "What is the color of the object?"
+img = "images/swarms.jpeg"
+
+## Initialize the workflow
+flow = Flow(
+    llm=llm,
+    max_loops="auto",
+    dashboard=True,
+)
+
+flow.run(task=task, img=img)