A new study reveals an AI-powered smart assistant capable of converting implicit knowledge and undocumented experiences in small and medium enterprises (SMEs) into formal process maps (BPMN 2.0). The system uses interactive dialogue to gather details and create and refine models in record time and at low cost, helping preserve institutional knowledge and enhance transparency.
Small and medium enterprises (SMEs) still rely heavily on implicit knowledge and practical experience that is rarely formally documented, putting them at risk of losing these valuable assets as staff changes. To address this challenge, researchers have introduced an innovative solution based on Large Language Models (LLMs) to capture this knowledge and convert it into standard process documentation.
The assistant, which is based on the "Gemini 2.5 Pro" model and a lightweight "Gradio" interface, works by conducting an interview-style dialogue with users in the work environment. It collects process details step-by-step, supports clarifying dialogue and on-demand analysis, and displays process maps (BPMN 2.0 diagrams) live and directly, allowing the user to improve and modify them in real-time. The system is designed to be interactive and incremental, facilitating the documentation process without significant burden.
An initial evaluation of the system in an equipment maintenance scenario showed impressive results. The smart assistant was able to produce an accurate model of the current state (AS-IS), identifying potential problems through explanatory annotations on the diagram itself, and then generate an improved model for the future state (TO-BE) – all within just about 12 minutes. Importantly, the total cost of API queries remained within a budget suitable for SMEs.
The study analyzes sources of delay and model selection trade-offs and proposes a roadmap towards developing the system to be more autonomous (Agentic) and capable of supporting multiple modalities. The results show that conversational large language models have the potential to lower the skill and cost barriers to accurate process documentation, helping organizations preserve their institutional knowledge, enhance operational transparency, and accelerate continuous improvement efforts.
Source: arXiv AI Papers | Exclusive coverage from AI Tools Oasis
Bringing you the latest news and analysis in the world of Artificial Intelligence with accuracy and credibility. Follow us for all updates.
OpenAI is advancing its ambitious super app project, aiming to integrate advanced AI capabilities into a single, multifunctional platform. This development is part of the company's strategy to expand services and deliver a unified user experience. Discover the full details and expected impact of this move.
Notion has restored access to its Anthropic AI integration after a 4-hour outage disrupted users relying on Claude-powered features. The incident highlights the growing dependency on AI productivity tools and raises questions about infrastructure stability. All user data remained secure during the disruption.
A new report from TechCrunch AI warns of a potential 'Tokenpocalypse'—a massive collapse of digital tokens due to oversupply. With over 80% of new tokens losing 90% of their value, the market faces a crisis reminiscent of the dot-com bubble. This analysis explores the risks, impacts, and how investors can protect themselves.
