Email Triage Assistant

Production System - Running 24/7

Overview

The Email Triage Assistant is an intelligent automation system that eliminates the daily burden of email management. By combining Claude AI's classification capabilities with a robust rules engine, it transforms incoming emails into actionable tasks without human intervention.

The Problem

Professional teams face a constant battle with email overload:

• Critical requests buried in promotional noise
• Action items forgotten in long thread chains
• Context lost when forwarding emails to project tools
• Hours wasted on manual sorting and task creation

The Solution

A production-grade system that runs continuously on personal VPN infrastructure, processing emails every 15 minutes:

Intelligent Classification

Claude AI analyzes each email against a trained skill matrix, determining:

• Category: Client request, internal task, notification, spam
• Priority: Urgent, high, normal, low
• Routing: Which team member or workflow should handle it
• Action Type: Requires response, task creation, or archive

Automated Task Creation

When an email requires action, the system:

1. Extracts key details (deadline, stakeholders, requirements)
2. Links relevant SOPs for self-service resolution
3. Creates properly formatted Asana tasks
4. Attaches the original email for context
5. Assigns based on skill-based routing matrix

Technical Architecture

Office 365 Inbox
       |
   [15-min Poll]
       |
  Microsoft Graph API
       |
   Claude AI Classifier
       |
   Rules Engine (SQLite)
       |
  Asana Task Creation
       |
   Email Notifications

Key Components

Email Monitor Service

• Systemd service running on Debian 12 VPN server
• Polls Microsoft Graph API every 15 minutes
• Tracks processed emails to prevent duplicates

AI Classification Engine

• Claude 3.5 Haiku for cost-effective classification
• Custom prompt engineering for business context
• Structured output parsing for reliable routing

Rules Database

• SQLite for routing rules and client associations
• Configurable skill matrix for team assignments
• SOP linking for common request types

Results

The system has been running in production since late 2024:

• ~30 minutes saved daily on email processing
• 100% capture rate of actionable items
• Zero missed client requests since deployment
• 24/7 operation with email failure alerts

Technical Highlights

• Stateless Design: Each poll is independent, enabling easy recovery
• Failure Resilience: AWS SES notifications on any processing errors
• Context Preservation: Full email thread linked to every task
• Cost Optimized: Haiku model keeps AI costs under $5/month

This project demonstrates production AI deployment, API orchestration across multiple platforms, and infrastructure automation running on personal VPN infrastructure.