Presented by SAP
In an era where anyone can spin up an LLM, the true differentiator isn’t the AI technology itself, however the institutional knowledge it’s grounded in. Internal and partner consultants leading operational transformation can’t risk hallucinated guidance when their recommendations impact integrated processes across supply chain, manufacturing, finance, and other core functions.
"Grounded AI is non-negotiable, because accuracy isn’t optional once we’re doing million-dollar transformation projects inside the SAP ecosystem, for instance," says Natalie Han, VP and chief product officer, gen AI at SAP Business AI. "Retrieval-augmented generation technology, and the flexibility to anchor responses in trusted enterprise knowledge, helps ensure accurate code interpretation, best-practice guidance, and clean-core decision support. It's how we bring real trust into AI-powered consulting."
A totally grounded AI assistant like SAP Joule for Consultants has tremendous value in production use cases, she adds. SAP Joule has terabytes of institutional data that's repeatedly curated and updated, so a consultant is assured they're getting up-to-the-minute SAP best practices and methodologies when counting on Joule, while at the identical time accelerating project delivery.
"We’re saving rework time by 14%, and saving consultants 1.5 hours per day per user, which is large whenever you consider how expensive consultants are actually," Han says. "Early adopters like Wipro have estimated they've saved 7 million hours on a manual basis for his or her consultants."
The inspiration of SAP Joule
SAP Joule is as certified as any consultant, says Sachin Kaura, chief architect, SAP Business AI. The tool was born in 2023, when GPTs famously passed a simulated bar exam and ignited buzz around the flexibility of LLMs to handle large amounts of context. It’s widely acknowledged that the SAP ecosystem, together with its associated domain ontology and taxonomy, is incredibly vast and might be very complex to navigate. The query became, how could an AI co-pilot be used to navigate that complexity when it was actually grounded inside the SAP ecosystem itself?
Sachin Kaura began experimenting with frontier LLM models by putting them through the identical certification exams SAP consultants take. The early results were poor, but after extensive context tuning and a concentrate on delivering value to the partner ecosystem, Joule now consistently scores 95% or higher.
"Not only were we testing from an information perspective, but we were in a position to work with all of our consultants to get what we call the golden data set," Han added. "It’s non-deterministic, language-based, and thoroughly grounded in human consultant expertise. We partnered with the entire consulting organization to manually label the golden data set across the entire products. That’s develop into the muse for every little thing we do even now."
A state-of-the-art indexing pipeline
Joule for Consultants stays up-to-date in real time. A state-of-the-art indexing pipeline pushes latest SAP documentation and release content into the model as soon because it’s published, giving consultants confidence that each answer reflects probably the most current guidance.
"That is pure engineering work done by our data scientists and engineers, using lots of underlying SAP technology," Kaura explains. "We leverage the SAP business foundation layer, document grounding services, and lots of purpose-built systems to remain on top of current events within the system."
SAP Business AI also has board-level alignment, ensuring this isn’t only a one-team effort but a company-wide priority. They’ve built strong internal partnerships with content owners across SAP — including SAP Learning, SAP Community, SAP Help, product teams, and consultant teams. Together, they repeatedly update proprietary content corresponding to SAP Notes, Knowledge Base Articles (KBAs), and other domain-specific guidance that reflects SAP’s evolving best practices.
All of this implies Joule for Consultants can take that repeatedly refreshed data and deliver answers in near real time. It's the form of research that may otherwise take a consultant hours. But information pulled directly from the source gives consultants probably the most current and authoritative guidance available, helping eliminate the early-stage missteps that may derail a project months later when scoping wasn’t aligned with the newest capabilities.
Ensuring enterprise-grade security
SAP is constructing a product that’s relevant, reliable, and responsible, Han says. As an organization founded in Europe, it takes data privacy seriously, adhering to the GDPR and other EU company regulations. On the core of SAP Business AI is the AI Foundation, the AI operating system that governs AI with built-in security, ethics, and orchestration, using automation and intelligence to administer lifecycles, optimize resources, and boost resilience.
All of the LLMs SAP and its customers use operate inside the AI foundation, which protects private and proprietary data from being leaked. Beyond data protection, SAP treats bias, ethics, and security at an enterprise level as well, with humans within the loop to run checks and balances.
"Now we have an enterprise-grade security framework in addition to prompt injection and guardrail testing," Kaura says. "The orchestration layer, built inside the AI Foundation, anonymizes inputs in addition to moderates them to forestall malicious content. That ensures that the output we give to our customers is relevant to the SAP ecosystem, relevant to the domain they’re asking about, and not only generic LLM excess. This set of tools, from the framework layer to the applying layer to the product standards, and in addition the very thorough testing is critical to securing our product. Then and only then can it reach our customers and partners."
Pushing the boundaries of Joule for Consultants
"We’re barely scratching the surface of what LLMs and agentic AI can offer," Han says. "Accessing knowledge is only the start. We’re going to have a much deeper understanding of consumers’ SAP systems and give you the chance to assist them implement and transform their journey. The product team and our engineers are working to make the tool more transformative, in a position to unearth more insights, connect with customers’ systems, and understand and optimize their processes, including generating code and handling customer code migration."
The following step is adding a second layer of grounding. SAP’s customer base is vast, and its partner ecosystem has implemented countless business scenarios. Grounding Joule in SAP’s institutional knowledge was the primary milestone; the subsequent is layering in each customer’s own proprietary context — historical system data, process designs, implementation blueprints, and internal documentation. This turns Joule from SAP-aware to customer-aware, delivering guidance that aligns with how a business actually operates.
“Consider it as grounding your knowledge on top of SAP knowledge — supplying you with more accurate and relevant guidance,” Kaura says. “Information that may otherwise be lost can sit on top of Joule for Consultants. Our system processes it and ensures it involves you in the proper manner and at the proper time.”
This expanded grounding also lets Joule adjust its guidance to the consultant’s role — whether or not they’re working as an architect, a functional consultant, or a technical consultant.
"We deliver the knowledge they need for a specific customer configuration," Han explains. "Then we will not only answer generic questions, but we will answer their particular configuration. From there it’s one step ahead to generating more insights and taking more actions."
Sponsored articles are content produced by an organization that’s either paying for the post or has a business relationship with VentureBeat, and so they’re all the time clearly marked. For more information, contact sales@venturebeat.com.
