Generating a Low-code Complete Workflow via Task Decomposition and RAG

TL;DR

This paper formalizes Task Decomposition and Retrieval-Augmented Generation as design patterns for GenAI systems, demonstrating their application in building a complex enterprise workflow generation system and discussing their impact on development practices.

Contribution

It introduces formalized design patterns for GenAI systems and shares industry experience applying them to a real-world workflow generation application.

Findings

Task Decomposition and RAG improve system flexibility and maintainability.

Application of patterns influences dataset creation, training, evaluation, and deployment.

Patterns help address safety and security considerations in GenAI development.

Abstract

AI technologies are moving rapidly from research to production. With the popularity of Foundation Models (FMs) that generate text, images, and video, AI-based systems are increasing their complexity. Compared to traditional AI-based software, systems employing FMs, or GenAI-based systems, are more difficult to design due to their scale and versatility. This makes it necessary to document best practices, known as design patterns in software engineering, that can be used across GenAI applications. Our first contribution is to formalize two techniques, Task Decomposition and Retrieval-Augmented Generation (RAG), as design patterns for GenAI-based systems. We discuss their trade-offs in terms of software quality attributes and comment on alternative approaches. We recommend to AI practitioners to consider these techniques not only from a scientific perspective but also from the standpoint of desired engineering properties such as flexibility, maintainability, safety, and security. As a second contribution, we describe our industry experience applying Task Decomposition and RAG to build a complex real-world GenAI application for enterprise users: Workflow Generation. The task of generating workflows entails generating a specific plan using data from the system environment, taking as input a user requirement. As these two patterns affect the entire AI development cycle, we explain how they impacted the dataset creation, model training, model evaluation, and deployment phases.