DESIGNING AUTONOMOUS LLM AGENT FRAMEWORKS USING GEN AI PIPELINES TO ENHANCE CUSTOMER SERVICE MANAGEMENT AND KNOWLEDGE WORKFLOWS

Abstract

Integrating autonomous agents within service management and service desk systems requires defining an appropriate operational model, context, scope, and specification. Autonomous agents are self-contained LLM AI applications fulfilling tasks and roles without user intervention. Generative AI frameworks and pipelines are models that describe the operational and interaction stages needed to fulfil predefined tasks using AI technologies. Each stage performs a well-defined operation that contributes to a complete process, enabling service integration and/or support. Environment-specific or domain knowledge provides the agent with the necessary context and enables support or service desk workflow decision-making. Conversational user experience design defines the standard of user interaction with the AI agent.

The proposed design explicitly maps the interaction and process stages within a generative AI pipeline. Service operation requirements inform the specific design scope, defining the basis for monitoring, maintenance, and reassessment of an LLMAI model used in an agent context. Framework performance and validation track essential operational characteristics and metrics required for modulating the service integration. The design has immediate application in customer service platforms and Cloud service marketplaces, where such models integrate autonomously with existing service portfolio offerings. The broader use case integrates LLMAI agents with service desk solutions used by organizations, enhancing the service desk environment, stimulating knowledge contributions, and enriching knowledge repositories.