How does a financial chatbot answer numerical questions without estimating them? A preview of the approach and functioning: The numbers come from fixed calculation methods and not from AI, and a countermeasure determines how reliable an answer is.
Read MoreAI in everyday work: Here's how to find the right start
AI in everyday work rarely fails with the tool itself, but with the constant need to learn. In the process, you are already bringing the most important part along: your expertise. Two prompts help you find the right starting point.
Read MoreAI assistant meets SAP Business One: Two paths out of the Versino AI shop
Claude, Copilot, and other AI assistants have arrived at the office. What they lack is SAP Business One. The Versino AI shop offers two ways to change that: the SAP B1 MCP for direct access to your data and the Versino Skills for verified SAP B1 expertise. Monthly subscription available starting at €5 per user.
Read MoreSprint and Swirl: How an AI agent divides work and learns from trials
This series deals with artificial intelligence in interaction with
Read MoreLATS: Considering several paths simultaneously with AI — and the availability check in SAP B1
This series focuses on artificial intelligence in conjunction with SAP Business One. Not as a collection of product announcements, but as an attempt to calmly consider fundamental AI principles and reflect on them using an example from everyday ERP use. This time, the topic is one that goes far beyond pure text generation. How does an AI model decide when a task requires not just a correct next sentence, but several steps that build upon each other? The technical term for this is Language Agent Tree Search, or LATS for short.
Read MoreReAct and RLEF: How Artificial Intelligence Learns from Real Mistakes — and What Automated Bank Reconciliation in SAP Business One Has to Do with It
This is the fourth episode in a series on this blog that deals with AI fundamentals in combination with SAP Business One. Up to now, it has mainly been about what a language model learns before it is even used: human ratings, trial and error, and the step-by-step checking of intermediate results. This episode reverses the perspective. It is about what happens while a model is already working, using a tool or having code executed, and how it reacts to what actually comes out of it. Two methods are at the centre that sound more similar than they actually are: ReAct and RLEF.
Read MoreSAP B1 10.0 FP2608: Service Layer AI as a transactional layer
With feature package 2608 for SAP Business One 10.0, SAP is extending this interface with conditional webhooks and enriched event payloads.
Read MoreProcess Reward Models: Why a correct result does not yet prove a correct method
This series continuously examines individual basic AI terms and methods, such as the Process Reward Model. The previous episode dealt with a sobering finding: generating is cheap, verifying is the actual bottleneck. A system can generate thousands of candidate answers in a short time; the real work only begins afterwards, when the correct answer has to be found among these candidates.
Read MoreTest-Time Compute Scaling: Why a Smaller AI Model Can End Up Winning — and What Supplier Comparison in SAP Business One Has to Do With It
This is a continuation of the series on this blog that deals with Artificial Intelligence in combination with SAP Business One. It is an attempt to calmly think through and clarify fundamental AI concepts. Each episode takes a concept from current AI research and ends by asking the same question: what of this actually reaches everyday ERP operations, and what remains vocabulary that sells well? The last episode was about verification and reward models. This time it is about a simpler, but surprisingly effective idea: simply asking the same question multiple times, or test-time compute scaling.
Read MoreRLHF and reward models: AI hype or what the approval process in SAP Business One has to do with it
This is the first post in a new series on this blog. It looks at the possibilities of artificial intelligence in direct interaction with SAP Business One — and not as a collection of product announcements, but as an attempt to think through fundamental AI topics calmly and thoroughly.
Read More