📧 Customer Email Agent

An intelligent, LLM-powered email classification and auto-response system built with LangChain and Groq (Llama 3.3 70B). The agent analyzes incoming customer emails, categorizes them, extracts key entities, performs sentiment analysis, and generates context-aware responses — all while maintaining per-sender conversational memory and built-in PII redaction.

📐 For detailed architecture, memory design, confidence logic, and escalation policy, see Design.md.

🚀 Getting Started

Prerequisites

• Python 3.9+
• A Groq API Key (free tier available at console.groq.com)

1. Clone the Repository

git clone https://github.com/3ismartyash/customer-email-agent.git
cd customer-email-agent

2. Install Dependencies

pip install -r requirements.txt

3. Configure Environment Variables

Create a .env file in the project root:

GROQ_API_KEY=your_groq_api_key_here

4. Run the Agent

python main.py --in data/sample_emails.json --out data/results.jsonl