Financial Coach (LangGraph)

A CLI agent that analyzes personal spending data and provides AI-powered financial coaching. Built with LangGraph for multi-step workflows.

What it does

This agent acts as a personal financial coach through a command-line interface. Users can:

Ask questions about their spending in natural language
Get breakdowns by category, merchant, or time period
Receive personalized recommendations and savings opportunities
Have multi-turn conversations with conversation memory

Example interaction:

You: Show me my spending by category

╔══════════════════════════════════════════════════════════╗
║           💡 FINANCIAL COACHING INSIGHTS                 ║
╚══════════════════════════════════════════════════════════╝

📊 YOUR SPENDING ANALYSIS
──────────────────────────────────────────────────────────────
  💰 Real Monthly Spending: $2,543.22
  🔴 Highest Expense: Rent @ $1,200.00 (47.2% of total)
  💡 Found 3 optimization opportunities totaling $425/month

💡 RECOMMENDATIONS FOR YOU
──────────────────────────────────────────────────────────────
  1. Your Rent is your largest expense (47.2%). This should be priority #1.
  2. Meal prep 2x/week could save $127/month (Highest impact)

Architecture

The agent uses a 4-node LangGraph workflow:

Enrich query - Adds context about time period, categories, and merchants
Query Snow Leopard - Converts natural language to SQL and retrieves data
Analyze and coach - Generates insights, recommendations, and follow-up questions
Format response - Creates formatted CLI output with Rich

Key components

LangGraph orchestrates the multi-step workflow
Snow Leopard handles natural language to SQL conversion
Coaching analyzer generates personalized financial insights
Memory manager maintains conversation context across turns
Rich CLI provides formatted terminal output

Run the example

Prerequisites

Python 3.10+
OpenAI API key
A Snow Leopard Cloud instance and API key
A PostgreSQL database that Snow Leopard Cloud can reach, such as a free Neon or Supabase database. See the PostgreSQL setup guide for details.

The example includes data/finance_coach.sql, a sample dataset built from the Kaggle Personal Finance dataset that covers January 2018 through September 2019. You can also use your own transaction data.

Setup

Clone the repository:

git clone https://github.com/SnowLeopard-AI/snowy-examples.git
cd snowy-examples/agent_examples/financial_coach_langchain

Install dependencies:

pip install -r requirements.txt

Load the sample dataset into your PostgreSQL database:

psql "postgresql://USER:PASSWORD@HOST/DBNAME?sslmode=require" -f data/finance_coach.sql

In Snow Leopard Cloud, add the database as a data source to your instance. Then create an API key on the Keys tab and copy the instance ID from the Connection Info tab. Create a .env file:

OPENAI_API_KEY=your-openai-key
SNOWLEOPARD_API_KEY=your-snowleopard-key
SNOWLEOPARD_INSTANCE_ID=your-instance-id

Run the agent:

python main.py

Example queries

The sample data covers January 2018 through September 2019, so ask about those months rather than “this month”.

“Show me my spending by category”
“Which merchants did I spend the most at?”
“Compare March 2019 vs February 2019”
“How much did I spend on groceries?”

Next steps

View the full source code on GitHub
Learn more about LangGraph
Explore the LangGraph quickstart

​What it does

​Architecture

​Key components

​Run the example

​Prerequisites

​Setup

​Example queries

​Next steps

What it does

Architecture

Key components

Run the example

Prerequisites

Setup

Example queries

Next steps