Jesús Barrasa

AI agents are only as smart as the context they access. Today’s data architectures suit humans who absorb knowledge from peers; agents cannot. The missing piece isn’t a better model, but persistent, governed context. A context graph captures what was decided, corrected, and learned across every interaction. This intelligence layer makes agents smarter over time, not just faster. Explore why context is the key to unlocking the value of agents.

Insert AbstractWhy do 95% of GenAI projects fail to reach production? Because an LLM without enterprise context is “brain-dead,” a powerful engine with no nervous system to connect it to business data. This explores why context engineering is the missing link, how Knowledge Graphs power GraphRAG to improve accuracy up to 3x, and how Prospa, Australia’s leading online business lender, cut loan approval times from 48 hours to 2 using this approach.

Modern AI applications struggle not because of a lack of models, but because meaning is implicit, fragmented, and brittle. In this talk, we’ll explore how making semantics explicit (using ontologies and knowledge graphs) changes how we design, build, and operate AI systems.

RAG has become one standard architecture component for GenAI applications to address hallucinations and integrate factual knowledge. While vector search over text is common, knowledge graphs represent a proven advancement by leveraging advanced RAG patterns to access and integrate interconnected factual information, complementing the language skills of LLMs.

You're trying to guide how your agents think and act. Code-orchestrated workflows are too rigid, but LLMs charting their own course feel too chaotic. When you need a middle ground, it’s time to reach for the secret weapon: ontologies. These graph-shaped fragments of actionable knowledge can fill in critical gaps.