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

# Anthropic Financial Analyst Thinking

> Analyze a stock portfolio with interleaved thinking, calculator, and YFinance tools.

```python financial_analyst_thinking.py theme={null}
"""
Anthropic Financial Analyst Thinking
====================================

Cookbook example for `anthropic/financial_analyst_thinking.py`.
"""

from agno.agent import Agent
from agno.models.anthropic import Claude
from agno.tools.calculator import CalculatorTools
from agno.tools.yfinance import YFinanceTools

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

# Complex multi-step reasoning problem that demonstrates interleaved thinking
task = (
    "I'm considering an investment portfolio. I want to invest $50,000 split equally "
    "between Apple (AAPL) and Tesla (TSLA). Calculate how many shares of each I can buy "
    "at current prices, then analyze what my total portfolio value would be if both stocks "
    "increased by 15%. Also calculate what percentage return that represents on my initial investment. "
    "Think through each step and show your reasoning process."
)

agent = Agent(
    model=Claude(
        id="claude-sonnet-4-20250514",
        thinking={"type": "enabled", "budget_tokens": 2048},
        betas=["interleaved-thinking-2025-05-14"],
    ),
    tools=[
        CalculatorTools(),
        YFinanceTools(),
    ],
    instructions=[
        "You are a financial analysis assistant with access to calculator and stock price tools.",
        "For complex problems, think through each step carefully before and after using tools.",
        "Show your reasoning process and explain your calculations clearly.",
        "Use the calculator tool for all mathematical operations to ensure accuracy.",
    ],
    markdown=True,
)

agent.print_response(task, stream=True)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

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

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

  <Step title="Export your Anthropic API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:ANTHROPIC_API_KEY="your_anthropic_api_key_here"
      ```
    </CodeGroup>
  </Step>

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

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

Full source: [cookbook/90\_models/anthropic/financial\_analyst\_thinking.py](https://github.com/agno-agi/agno/blob/main/cookbook/90_models/anthropic/financial_analyst_thinking.py)