Why SAP says enterprise AI agents need knowledge graphs and governance
Our take
The conversation between SAP’s Max McPhee and VentureBeat Research’s Rob Stretchay at VB Transform 2026 highlights a crucial shift in the enterprise AI landscape: the move from simple chatbots to truly autonomous AI agents capable of executing complex business processes. This isn't just about clever conversation; it's about enabling AI to *do* work, and the key differentiator, according to McPhee, is grounding these agents in a company’s unique context. We're seeing this play out broadly – Google’s AI search is rapidly becoming the default [Google’s AI search is rapidly becoming the default, new data shows], demonstrating the increasing user acceptance of AI-driven solutions. However, the enterprise needs something far more specific than a general understanding of the world; it needs an AI that understands *its* world. This contrasts sharply with the current state where many enterprise chat software solutions fall short, struggling to grasp internal jargon and processes, and prompting users to explain basic acronyms. US AI Dominance Is Over [US AI Dominance Is Over: Here's Why], underlining the importance of tailored solutions.
McPhee’s emphasis on knowledge graphs and vector-embedded data as the foundation for this contextual understanding is particularly insightful. It’s an analogy to onboarding a new employee – providing the agent with the necessary background knowledge and tribal wisdom. This approach moves beyond simply providing data; it's about structuring that data in a way that allows the AI to efficiently retrieve and apply relevant information. The integration of acquisitions like LeanIX, which provides a "Google Maps for your architecture," and Signavio, focused on process mining, further underscores SAP’s commitment to mapping and understanding the complex interconnections within enterprise systems. The company’s investment in n8n, embedded within Joule Studio, exemplifies their vision of a low-code environment empowering businesses to build and customize these intelligent agents. This isn't about replacing existing systems but about augmenting them with AI that understands their nuances.
The discussion also rightly points to the vital importance of governance, identity, and security. SAP’s long history in process control provides a strong foundation for managing the risks associated with autonomous agents. The need for machine learning-based validation – a “revival” of ML, as McPhee put it – demonstrates a pragmatic approach to ensuring agent behavior aligns with established processes and policies. The requirement for both the human user *and* the AI agent to possess the necessary permissions to access systems is a crucial safeguard against circumventing security controls. This layered approach, combining established governance frameworks with AI-powered monitoring and validation, is essential for building trust and ensuring responsible AI adoption within the enterprise. Netflix Details Its In-House LLM Serving Platform with Triton and vLLM [Netflix Details Its In-House LLM Serving Platform with Triton and vLLM], showcasing how even sophisticated platforms require robust infrastructure and validation to ensure reliable performance.
Looking ahead, the challenge lies in modernizing legacy systems to fully leverage the potential of autonomous AI agents. McPhee’s analogy of driving a Ferrari on a dirt track is apt – upgrading the infrastructure is a prerequisite for unlocking true performance. The question isn't just about implementing AI; it’s about creating an environment where AI can thrive, seamlessly integrating with existing systems and processes. As enterprises increasingly rely on AI agents to automate workflows and drive decision-making, ensuring data accessibility, robust governance, and adaptable infrastructure will be paramount to realizing the transformative benefits promised by this emerging technology.
Presented by SAP
At VB Transform 2026, Max McPhee, senior solution advisor at SAP, spoke with Rob Stretchay, lead analyst at VentureBeat Research, about what it takes for enterprises to move beyond chatbots to autonomous AI agents that can execute real business processes. He argued that the difference comes down to grounding those agents in a company’s own context rather than general knowledge.
https://www.youtube.com/watch?v=SRf9t-wSZSo
"Where we're starting to see more emergent behavior of it feeling like a coworker rather than an assistant, is where we're able to provide context on the actual enterprise rather than being able to use more of the standard knowledge," McPhee said.
That's the gap that still separates most enterprise chat software from genuinely agentic systems.
Building enterprise context with knowledge graphs
The same principles companies use to onboard new employees also apply to agents, adapted for software that retrieves information differently than humans do.
"When you are onboarding a new agent, I think it's important to acknowledge how you might onboard a new employee, but tune that for an agent," McPhee said. "The way that is really powerful is using knowledge graphs and having vector-embedded data, because that's a really easy format for an agent to be able to find and retrieve information."
That same grounding is also what keeps an agent from stumbling over an enterprise's internal shorthand, a problem that's acute in SAP's world.
"Being able to provide that tribal knowledge in the format that's easy for it to consume helps to provide a really nice result with your agents versus a chatbot that might say, 'Well, what does that acronym mean?'" he said.
Bringing governance, identity, and security to autonomous agents
Governance is an area where SAP's history works in its favor, and the controls have been evolving for systems that act with more flexibility than earlier automation did.
"That's where SAP really has a good home, around that governance and process control," McPhee said. We're a 50-year-old process company, modernizing that governance to be able to handle the flexibility that comes with agents running."
One consequence is a renewed role for machine learning in validating agent behavior.
"It's becoming a bit of a revival of machine learning," he added, pointing to customers that run agents within a process but then layer in anomaly detection and machine-learning-based validation as a guardrail. This is the same approach SAP had long used for intelligent approval recommendations.
Identity and permissions carry that governance into execution. Under this model, both the human and SAP’s Joule, the generative AI assistant embedded across the company’s cloud applications and Business Technology Platform, must hold the rights to access a given system. Even if a user has permission to access S/4, they cannot do so through Joule unless the assistant has also been provisioned for that access, closing off the risk of using an agent to route around access controls.
Balancing standard SAP with customized enterprise landscapes
Much of McPhee’s work involves reconciling SAP’s own knowledge with decades of customer customization and non-SAP systems. As he put it, many customers tell SAP, “You’re only 10% of my landscape,” a reality that has shaped the company’s recent strategy.
Recent acquisitions such as LeanIX, which McPhee likened to “Google Maps for your architecture,” and process-mining company Signavio are intended to help map that non-SAP majority so SAP’s agents can understand how enterprise systems interconnect. The company has also invested in Berlin-based automation company n8n and is embedding it natively into Joule Studio, its intent-based, low-code environment for building agents.
McPhee warned that companies also need to modernize older on-premises systems or risk running into limitations as they expand the use of autonomous agents.
"You're going to probably run into throughput issues, and you're kind of trying to drive a Ferrari around a dirt track," he said. "You've got to upgrade the track first if you want to drive a Ferrari."
Sponsored articles are content produced by a company that is either paying for the post or has a business relationship with VentureBeat, and they’re always clearly marked. For more information, contact sales@venturebeat.com.
Read on the original site
Open the publisher's page for the full experience