Presentation: From Retrieval to Reasoning: Building Production-Ready Agentic AI Systems with Knowledge Graphs
Computer ScienceData ScienceInformation Systems
THE AI ANGLE
Operating as autonomous agents taking over software development and reasoning tasksCassie Shum outlines an architectural shift from using knowledge graphs merely for retrieval to employing them as the structural reasoning foundation for agentic AI systems. She presents patterns such as decision provenance, context bundling, and agent visibility to resolve issues with long-context LLM prompting like inconsistency and lack of auditability. For computing and information systems educators, this highlights how foundational data modeling techniques remain vital for governing and stabilizing autonomous AI in software engineering.
THE TEACHING ANGLE
Students can explore the architectural trade-offs between relying on massive LLM prompt windows versus using structured knowledge graphs to ensure consistency, accountability, and multi-domain dependency tracking in autonomous systems.Read the original at infoq.com Generate teaching or study materials
More in Computer Science
- Early Anthropic hire, former METR COO have found a way to rein in rogue AI agentsTechCrunch · September 15, 2026
- AI’s best coding agent fails 60% of the time — and the data backs it upThe New Stack · September 15, 2026
- The ERP reckoning: Decades of customization could block AI valueCIO.com · September 15, 2026
- Open weights are not open source: Why AI's favorite label is under disputeThe Register · September 15, 2026
- Exclusive: Paying for frontier AI models buys 4-month head start at 5x the costArs Technica · September 15, 2026