> ## Documentation Index
> Fetch the complete documentation index at: https://agno-v2-service-account.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Trolley Problem Analysis

> Demonstrates built-in and DeepSeek-backed reasoning for ethical analysis.

```python trolley_problem.py theme={null}
"""
Trolley Problem Analysis
========================

Demonstrates built-in and DeepSeek-backed reasoning for ethical analysis.
"""

from agno.agent import Agent
from agno.models.deepseek import DeepSeek
from agno.models.openai import OpenAIChat

# ---------------------------------------------------------------------------
# Create Agents
# ---------------------------------------------------------------------------
cot_prompt = (
    "Solve the trolley problem. Evaluate multiple ethical frameworks. "
    "Include an ASCII diagram of your solution."
)

deepseek_prompt = (
    "You are a philosopher tasked with analyzing the classic 'Trolley Problem'. In this scenario, a runaway trolley "
    "is barreling down the tracks towards five people who are tied up and unable to move. You are standing next to "
    "a large stranger on a footbridge above the tracks. The only way to save the five people is to push this stranger "
    "off the bridge onto the tracks below. This will kill the stranger, but save the five people on the tracks. "
    "Should you push the stranger to save the five people? Provide a well-reasoned answer considering utilitarian, "
    "deontological, and virtue ethics frameworks. "
    "Include a simple ASCII art diagram to illustrate the scenario."
)

cot_agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    reasoning=True,
    markdown=True,
)

deepseek_agent = Agent(
    model=OpenAIChat(id="gpt-4o"),
    reasoning_model=DeepSeek(id="deepseek-reasoner"),
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agents
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    print("=== Built-in Chain Of Thought ===")
    cot_agent.print_response(cot_prompt, stream=True, show_full_reasoning=True)

    print("\n=== DeepSeek Reasoning Model ===")
    deepseek_agent.print_response(deepseek_prompt, stream=True)
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno openai
    ```
  </Step>

  <Step title="Export your API keys">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export DEEPSEEK_API_KEY="your_deepseek_api_key_here"
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:DEEPSEEK_API_KEY="your_deepseek_api_key_here"
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run the example">
    Save the code above as `trolley_problem.py`, then run:

    ```bash theme={null}
    python trolley_problem.py
    ```
  </Step>
</Steps>

Full source: [cookbook/10\_reasoning/agents/trolley\_problem.py](https://github.com/agno-agi/agno/blob/main/cookbook/10_reasoning/agents/trolley_problem.py)