diff --git a/README.md b/README.md
index a2b22dc..ede3c07 100644
--- a/README.md
+++ b/README.md
@@ -24,6 +24,8 @@ From the /scripts directory:
     Example: `poetry run python send_message.py 'I want to fly from San Francisco'`
 
     NOTE: The workflow will pause on the 'confirm' step until the user sends a 'confirm' signal. Use the 'get_tool_data' query to see the current state of the workflow.
+
+    You can send a 'confirm' signal using `poetry run python send_confirm.py`
 5. Get the conversation history summary by querying the workflow.
     
     Example: `poetry run python get_history.py`
@@ -36,4 +38,5 @@ Run query get_tool_data to see the data the tool has collected so far.
 ## TODO
 - The LLM prompts move through 3 mock tools (FindEvents, SearchFlights, CreateInvoice) but I should make them contact real APIs.
 - Might need to abstract the json example in the prompt generator to be part of a ToolDefinition (prevent overfitting to the example).
-- I need to build a chat interface so it's not cli-controlled. Also want to show some 'behind the scenes' of the agents being used as they run.
\ No newline at end of file
+- I need to build a chat interface so it's not cli-controlled. Also want to show some 'behind the scenes' of the agents being used as they run.
+- What happens if I don't want to confirm a step, but instead want to correct it? TODO figure out
\ No newline at end of file
diff --git a/scripts/send_confirm.py b/scripts/send_confirm.py
new file mode 100644
index 0000000..22be926
--- /dev/null
+++ b/scripts/send_confirm.py
@@ -0,0 +1,20 @@
+import asyncio
+import sys
+from temporalio.client import Client
+
+
+async def main():
+
+    # 1) Connect to Temporal and signal the workflow
+    client = await Client.connect("localhost:7233")
+
+    workflow_id = "agent-workflow"
+
+    await client.get_workflow_handle(workflow_id).signal("confirm")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 1:
+        print("Usage: python send_confirm.py'")
+    else:
+        asyncio.run(main())