> ## Documentation Index
> Fetch the complete documentation index at: https://agentcontrol-docs-add-source-code-notes-to-examples.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Steer Action Demo

> Banking transfer agent showcasing allow, deny, warn, and steer actions.

<Info>
  The source code for this example is available on GitHub:
  [Steer Action Demo](https://github.com/agentcontrol/agent-control/tree/main/examples/steer_action_demo)
</Info>

A realistic banking agent that processes wire transfers with compliance controls, fraud detection, and approval workflows.

## What It Demonstrates

* Allow for low-risk transfers
* Deny for compliance violations (OFAC sanctions, high fraud)
* Warn for suspicious activity without blocking
* Steer for approval workflows (2FA, manager approval)

## Prerequisites

* Python 3.12+
* `uv` installed
* Agent Control server running
* `OPENAI_API_KEY` set in your environment

## Run The Demo

```bash theme={null}
cd examples/steer_action_demo

# One-time setup

uv run setup_controls.py

# Interactive banking agent

uv run autonomous_agent_demo.py
```

## Try These Scenarios

1. Simple transfer: "Send \$500 to Jane Smith"
2. Sanctioned destination: "Wire \$5,000 to North Korea"
3. Large transfer: "Transfer \$15,000 to contractor in UK"

## Files

| File                       | Description                |
| :------------------------- | :------------------------- |
| `setup_controls.py`        | Creates the demo controls  |
| `autonomous_agent_demo.py` | Interactive banking agent  |
| `interactive_demo.py`      | CLI demo with manual steps |