diff --git a/examples/workflows/workflow_intent_classifier/README.md b/examples/workflows/workflow_intent_classifier/README.md
index d09333940..dd5ee58de 100644
--- a/examples/workflows/workflow_intent_classifier/README.md
+++ b/examples/workflows/workflow_intent_classifier/README.md
@@ -51,3 +51,65 @@ Run your MCP Agent app:
 ```bash
 uv run main.py
 ```
+
+## `4` [Beta] Deploy to the cloud
+
+### `a.` Log in to [MCP Agent Cloud](https://docs.mcp-agent.com/cloud/overview)
+
+```bash
+uv run mcp-agent login
+```
+
+### `b.` Update your `mcp_agent.secrets.yaml` to mark your developer secrets (keys)
+
+```yaml
+openai:
+  api_key: !developer_secret
+# Other secrets as needed
+```
+
+### `c.` Deploy your agent with a single command
+```bash
+uv run mcp-agent deploy workflow-intent-classifier
+```
+
+### `d.` Connect to your deployed agent as an MCP server through any MCP client
+
+#### Claude Desktop Integration
+
+Configure Claude Desktop to access your agent servers by updating your `~/.claude-desktop/config.json`:
+
+```json
+"my-agent-server": {
+  "command": "/path/to/npx",
+  "args": [
+    "mcp-remote",
+    "https://[your-agent-server-id].deployments.mcp-agent-cloud.lastmileai.dev/sse",
+    "--header",
+    "Authorization: Bearer ${BEARER_TOKEN}"
+  ],
+  "env": {
+        "BEARER_TOKEN": "your-mcp-agent-cloud-api-token"
+      }
+}
+```
+
+#### MCP Inspector
+
+Use MCP Inspector to explore and test your agent servers:
+
+```bash
+npx @modelcontextprotocol/inspector 
+```
+
+Make sure to fill out the following settings:
+
+| Setting | Value | 
+|---|---|
+| *Transport Type* | *SSE* |
+| *SSE* | *https://[your-agent-server-id].deployments.mcp-agent-cloud.lastmileai.dev/sse* |
+| *Header Name* | *Authorization* | 
+| *Bearer Token* | *your-mcp-agent-cloud-api-token* |
+
+> [!TIP]
+> In the Configuration, change the request timeout to a longer time period. Since your agents are making LLM calls, it is expected that it should take longer than simple API calls.
diff --git a/examples/workflows/workflow_intent_classifier/main.py b/examples/workflows/workflow_intent_classifier/main.py
index c43ad4631..5203c071b 100644
--- a/examples/workflows/workflow_intent_classifier/main.py
+++ b/examples/workflows/workflow_intent_classifier/main.py
@@ -12,8 +12,15 @@
 
 app = MCPApp(name="intent_classifier")
 
-
-async def example_usage():
+@app.tool
+async def example_usage()->str:
+    '''
+    this is an example function/tool call that uses the intent classification workflow.
+    It uses both the OpenAI embedding intent classifier and the OpenAI LLM intent classifier
+    '''
+    
+    results=""
+    
     async with app.run() as intent_app:
         logger = intent_app.logger
         context = intent_app.context
@@ -35,12 +42,13 @@ async def example_usage():
             context=context,
         )
 
-        results = await embedding_intent_classifier.classify(
+        output = await embedding_intent_classifier.classify(
             request="Hello, how are you?",
             top_k=1,
         )
 
-        logger.info("Embedding-based Intent classification results:", data=results)
+        logger.info("Embedding-based Intent classification results:", data=output)
+        results="Embedding-based Intent classification results: " + ", ".join(r.intent for r in output)
 
         llm_intent_classifier = OpenAILLMIntentClassifier(
             intents=[
@@ -58,13 +66,15 @@ async def example_usage():
             context=context,
         )
 
-        results = await llm_intent_classifier.classify(
+        output = await llm_intent_classifier.classify(
             request="Hello, how are you?",
             top_k=1,
         )
 
-        logger.info("LLM-based Intent classification results:", data=results)
+        logger.info("LLM-based Intent classification results:", data=output)
+        results+="LLM-based Intent classification results: " + ", ".join(r.intent for r in output)
 
+    return results
 
 if __name__ == "__main__":
     import time