Building Specialized Software-Assistant ChatBot with Graph-Based Retrieval-Augmented Generation
This addresses the need for automated, reliable digital adoption platforms to reduce manual effort in training employees on complex enterprise software, though it is incremental as it builds on existing RAG methods with a graph-based adaptation.
The paper tackles the problem of unreliable LLM-generated assistance for enterprise software by introducing a Graph-based Retrieval-Augmented Generation framework that automatically converts software interfaces into knowledge graphs, resulting in grounded and context-aware guidance as demonstrated in industrial collaborations.
Digital Adoption Platforms (DAPs) have become essential tools for helping employees navigate complex enterprise software such as CRM, ERP, or HRMS systems. Companies like LemonLearning have shown how digital guidance can reduce training costs and accelerate onboarding. However, building and maintaining these interactive guides still requires extensive manual effort. Leveraging Large Language Models as virtual assistants is an appealing alternative, yet without a structured understanding of the target software, LLMs often hallucinate and produce unreliable answers. Moreover, most production-grade LLMs are black-box APIs, making fine-tuning impractical due to the lack of access to model weights. In this work, we introduce a Graph-based Retrieval-Augmented Generation framework that automatically converts enterprise web applications into state-action knowledge graphs, enabling LLMs to generate grounded and context-aware assistance. The framework was co-developed with the AI enterprise RAKAM, in collaboration with Lemon Learning. We detail the engineering pipeline that extracts and structures software interfaces, the design of the graph-based retrieval process, and the integration of our approach into production DAP workflows. Finally, we discuss scalability, robustness, and deployment lessons learned from industrial use cases.