Blog

Artificial intelligence is not only changing the way we develop software, it is also changing the way we use software. For BCS, our project management and ERP software, this means that AI should make everyday work noticeably easier, reduce routine tasks, guide users to answers more quickly, and increase internal efficiency. While many AI initiatives focus on one-off solutions or experimental prototypes, Projektron pursues a systematic, long-term approach.

With BCS AI assistance, we at Projektron have developed our first productive AI application that enables users to quickly and reliably obtain answers to questions about BCS documentation. The path to this point was iterative: Several rounds of testing and improvement showed that it is not the language model itself, but rather retrieval, splitting, and data preparation that determine the quality of the answers. This article shows how we at Projektron optimized the system step by step – right up to its productive use by customers.

Over the past few months, Projektron has been working intensively on developing a powerful and future-proof AI framework for BCS. After presenting our initial experiments with language models, RAG concepts, and prompt engineering in previous articles, we are now focusing on how these findings can be used to create a robust, productive system architecture.

Since the end of 2023, we at Projektron GmbH have been exploring the possibilities of AI—how can we make this technology usable for our ERP and project management software BCS? In a development project, we familiarized ourselves with the technology and worked out some basics for possible product applications.

Guest article by Franziska Hinze, IAPM – In project management, there is a wide range of certifications available. They serve as visible proof of solid competencies and confirm a deep understanding of the discipline. At the same time, they act as catalysts for both personal and organizational development by demonstrating mastery of established methods and practices. This, in turn, can significantly enhance career opportunities. The following article explores the benefits and limitations that certifications can bring to both learning and professional practice.

The Project Management Institute (PMI) PMBOK® Guide is one of the world's most widely recognized reference works in project management. The latest editions of the guide represent a fundamental evolution: away from a purely process-oriented set of rules and toward a principles-, values-, and context-oriented framework. The current edition builds on this change and combines fundamental guiding principles, key performance areas, and modern, non-prescriptive process guidance. As a result, the PMBOK® Guide is now equally suitable for classic, agile, and hybrid project environments. The focus is less on the question of exactly which steps to take and more on how project managers can make situation-appropriate decisions and create sustainable value. But how can the PMBOK Guide be optimally implemented in practice?

Language models such as GPT, BERT, and LLaMA have impressive language comprehension skills. They can summarize, formulate, or translate texts—and even show a touch of style awareness. But one crucial disadvantage remains: the knowledge of these models ends at the point of training. So they still know who discovered America, but not who just won the soccer championship or what new AI developments are currently making the rounds. Company-specific information is also left out. For example, a standard model cannot answer questions about the latest BCS releases. This is where RAG (Retrieval-Augmented Generation) comes into play. RAG gives the language model access to current or subject-specific information. This means that AI can not only draw on its pre-trained knowledge, but also on current data that is specifically relevant to the task at hand.