Let the Agent Do the Math: Expense Insights

You've been manually tracking your monthly expenses in a spreadsheet, but analyzing spending patterns takes forever.

Your friend recommended trying smolagents to automate the analysis. Your weekly expense data for the past month is given in the following expense_data dictionary:

expense_data = {
    "groceries": [120, 95, 110, 140],
    "utilities": [85, 92, 78, 88],
    "entertainment": [45, 0, 75, 30],
    "transportation": [60, 55, 70, 65]
}

Let's run an agent that can help you understand your spending habits and create a budget plan.

Note: The agent and expense_data dictionary have been already initialized for you.

This exercise is part of the course

AI Agents with Hugging Face smolagents

Exercise instructions

Run the provided code to see smolagents analyze your expense data.
Observe the output and how the agent writes Python code to find spending patterns.

Hands-on interactive exercise

Have a go at this exercise by completing this sample code.

# Task for the agent
task = f"""Analyze my monthly expense data by category. Calculate total spending per category, find my highest expense area, and suggest a realistic budget for next month. Use simple text format in your final answer. Here is my weekly expense data for the past four weeks:

{expense_data}
"""

# Execute the financial analysis
result = agent.run(task)

print("Personal finance analysis:\n")
print(result)

Edit and Run Code

This exercise is part of the course

AI Agents with Hugging Face smolagents

AdvancedSkill Level

5.0+

Start Course for Free

Discover what makes code agents special and how they use Python to reason and act. Build your first agent with smolagents, add built-in and community tools for web access, and create custom tools to connect agents with data.

Exercise 1: Introduction to Hugging Face smolagents Exercise 2: Let the Agent Do the Math: Expense Insights

Current Exercise

Exercise 3: Wait, You Didn't Write Any Functions?Exercise 4: Creating an Agent With Tools Exercise 5: Writing Code Through Prompts: Compound Interest Exercise 6: Let Agents Search the Web Exercise 7: Creating an Agent With Custom Tools Exercise 8: Just Add @tool: Writing a Custom Tool Exercise 9: Check, Please! Giving Agents Access to Data Exercise 10: One Prompt, Many Tools

Transform your traditional RAG pipeline into an agentic system that retrieves information iteratively and reasons across multiple steps. Build stateful tools to support advanced retrieval, guide agents with planning intervals to improve outcomes, and use callbacks to track and customize agent behavior at runtime.

Exercise 1: RAG Refresher Exercise 2: RAG in Order: From Manuals to Answers Exercise 3: So, What’s Actually Happening in RAG?Exercise 4: The Step That Adds Meaning Exercise 5: Introduction to Agentic RAG Exercise 6: Stateful by Design: Build a RAG Search Tool Exercise 7: Connect the Tool, Unlock Agentic RAG Exercise 8: Working With Multi-Step Agents Exercise 9: Track Agent Steps, Monitor the Action Exercise 10: Game Time: Run the Full Agent

Tackle complex workflows by orchestrating teams of specialized agents under a coordinating manager. Add memory to retain context across interactions, debug agent behavior using execution traces and reasoning steps, and implement robust validation strategies to ensure high-quality, reliable responses.

Exercise 1: Introduction to Multi-Agent Systems Exercise 2: Divide and Conquer: Creating Specialist Agents Exercise 3: Meet the Team: Agent Coordination Exercise 4: Managing Agent Memory Exercise 5: Don't Forget: Keeping Memory Between Calls Exercise 6: Tracing the Agent’s Code Execution Exercise 7: Agent Final Answer Validation Exercise 8: Say More, Agent: Enforcing Answers Length Exercise 9: Smarter Agents: Validate and Retry Exercise 10: Congratulations!