Author: Chidambara Raju G
Version: 1.0
Project Repository: Capital Compass

🔍 Abstract

Capital Compass is an agentic AI application that automates the end-to-end workflow of investment research.
It leverages a multi-agent LangGraph workflow to fetch financial data, analyze news sentiment, perform web-based analyst research, and synthesize these inputs into a decisive investment report.

By orchestrating specialized agents—financial, sentiment, and web research analysts—along with a critique and synthesis layer, Capital Compass generates professional-grade reports with clear recommendations for investors.

This project demonstrates the practical use of agentic AI in financial services, combining structured data APIs, LLM-driven analysis, and workflow orchestration to address the complexity and subjectivity inherent in investment decision-making.

🎯 Problem Statement

Investment research is traditionally:

• ⏳ Time-consuming → Analysts must gather data from multiple sources (financial metrics, news sentiment, analyst ratings).
• 🔗 Fragmented → Quantitative metrics and qualitative news often remain siloed.
• ⚖️ Subjective → Bias creeps in when individuals interpret data inconsistently.

The challenge was to design an AI-driven system that:

1. Automates the multi-step data gathering and analysis.
2. Ensures a balanced review of opportunities and risks.
3. Produces actionable, decisive recommendations instead of neutral summaries.

🧭 Solution Overview – Capital Compass

Capital Compass solves this problem using an agentic multi-step workflow powered by LangGraph.

Core Capabilities

• 🤖 Automated Data Fetching – Pulls company financials and news sentiment from Alpha Vantage API and analyst ratings from Tavily Search.
• 📊 Specialized Analysis Agents:
  • Financial Analyst → Evaluates company fundamentals.
  • Sentiment Analyst → Summarizes market/news perception.
  • Web Research Analyst → Extracts consensus ratings and targets.
• 🧮 Critique Agent – Distills the strongest opportunity vs. the most significant risk.
• 📝 Final Report Agent – Weighs all inputs to provide a clear “Invest / Do Not Invest / Hold” recommendation.

🚀 Live Demo

🎯 Workflow Diagram

%%{init: {
  "theme": "dark",
  "themeVariables": {
    "primaryColor": "#0b1220",
    "primaryTextColor": "#E5E7EB",
    "primaryBorderColor": "#93C5FD",
    "lineColor": "#93C5FD",
    "tertiaryColor": "#111827",
    "fontSize": "12px",          /* Slightly smaller text */
    "padding": 12,               /* More space inside nodes */
    "nodeSpacing": 60,           /* Wider horizontal spacing */
    "rankSpacing": 60,           /* Wider vertical spacing */
    "fontFamily": "Inter, ui-sans-serif, system-ui, -apple-system, Segoe UI, Roboto"
  }
}}%%

graph TD
    A[Start:<br/>User Enters Ticker] --> B[Fetch:<br/>Financial Overview]
    A --> C[Fetch:<br/>News & Sentiment]
    A --> I[Fetch:<br/>Web Search]

    B --> D{Analyze:<br/>Financials}
    C --> E{Analyze:<br/>Sentiment}
    I --> J{Summarize:<br/>Web Research}

    D --> F[Balanced Review:<br/>Risk & Opportunity]
    E --> F
    J --> F

    F --> G[Final Synthesis:<br/>Generate Report]
    G --> H[End:<br/>Display Report]

    %% Dark-friendly styles
    classDef fetch fill:#0F172A,stroke:#818CF8,color:#E5E7EB,stroke-width:2px
    classDef websearch fill:#1E1B4B,stroke:#A5B4FC,color:#E0E7FF,stroke-width:2px
    classDef analyze fill:#111827,stroke:#60A5FA,color:#E5E7EB,stroke-width:2px
    classDef critic fill:#1F0A0A,stroke:#FCA5A5,color:#FEE2E2,stroke-width:2px
    classDef final fill:#052E2B,stroke:#34D399,color:#D1FAE5,stroke-width:2px
    classDef default fill:#0B1220,stroke:#93C5FD,color:#E5E7EB,stroke-width:1.5px

    class B,C fetch
    class I websearch
    class J analyze
    class D,E analyze
    class F critic
    class G final

🛠️ How It Works (Architecture)

The core of Capital Compass is a stateful graph built with LangGraph. This orchestrates a sophisticated workflow between specialized AI agents to ensure a robust and nuanced analysis.

1. Parallel Information Gathering

The process begins by simultaneously gathering three distinct types of information:

• 📊 Financial Overview: Fetches quantitative financial data from Alpha Vantage.
• 📰 News & Market Sentiment: Fetches qualitative news and sentiment from Alpha Vantage.
• 🔍 Forward-Looking Insights: Performs a targeted web search for analyst ratings and price targets.

2. Specialized Analysis

The raw data is then processed in parallel by three specialist agents:

• 👨‍💼 Financial Analyst Agent → Interprets financial metrics.
• 🧠 Sentiment Analyst Agent → Evaluates news and market perception.
• 🌐 Web Research Agent → Summarizes findings from the web search.

3. Balanced Review

All three analyses are passed to the Risk & Opportunity Analyst.

• 🎯 Role: Distill everything into:
  • The most compelling reason to invest.
  • The most significant risk.

4. Final Synthesis

Finally, the Senior Advisor Agent receives:

• The specialist analyses
• The balanced review

It then weighs the core opportunity against the significant risk to produce a structured, decisive investment report.

💻 Technology Stack

• Frontend: Streamlit
• AI Orchestration: LangChain / LangGraph
• LLM Provider: Groq (multi-model support)
• Data Source: Alpha Vantage API
• Core Language: Python
• Tools: Tavily Web Search

⚙️ Setup and Installation

Follow these steps to get a local copy running:

Prerequisites

• Python 3.11+
• Alpha Vantage API Key
• Groq API Key
• Tavily API Key

Installation

Clone the repository:

git clone https://github.com/ChidambaraRaju/capital-compass
cd capital-compass

Create a virtual environment:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

Install dependencies:

pip install -r requirements.txt

Set up environment variables:

Create a .env file in the project root with:

ALPHAVANTAGE_API_KEY="YOUR_ALPHA_VANTAGE_KEY"
GROQ_API_KEY="YOUR_GROQ_API_KEY"
TAVILY_API_KEY="YOUR_TAVILY_API_KEY"

▶️ Usage

Run the Streamlit app from the root directory:

streamlit run main.py

📁 Project Structure

.
├── assets/
│   └── logo.png
├── capital_compass/
│   ├── agents/
│   │   ├── analysis_agents.py
│   │   └── data_fetcher.py
│   ├── tools/
│   │   ├── alpha_vantage_client.py
        └── tavily_search_tool.py
│   ├── exceptions.py
│   ├── graph.py
│   └── state.py
├── .env
├── main.py
└── requirements.txt

📄 License

Distributed under the MIT License.

✨ Acknowledgements

• Groq
• Alpha Vantage

Made with ❤️ and Python