ETD

• asynchronous messaging
• business process automation
• document analysis
• email automation
• event-driven architecture
• intelligent process automation
• large language models
• microservices architecture
• model context protocol
• multi-agent systems
• natural language processing

This thesis presents the design and implementation of an automated system for managing email requests in the water utility sector, leveraging a microservices architecture and intelligent agents. The system integrates Large Language Models (LLMs) for natural language processing and computer vision techniques for document analysis, orchestrated through Apache Kafka to ensure scalability and resilience. The proposed solution aims to reduce processing times, operational costs, and human errors associated with manual request handling, thereby enhancing customer service quality. The architecture, implementation details, testing strategies, and results are discussed in depth, highlighting the system's effectiveness in automating complex workflows.