AI Business LensTHE BUSINESS OF AI, FOR PEOPLE WHO TEACH IT OR LEARN FROM IT
InfoQ · September 13, 2026

Presentation: From Retrieval to Reasoning: Building Production-Ready Agentic AI Systems with Knowledge Graphs

Computer ScienceData ScienceInformation Systems
THE AI ANGLE
Executing autonomous agentic workflows and decision-making within software systems

Cassie Shum details how knowledge graphs serve as a foundational architecture for agentic AI systems beyond simple retrieval, highlighting patterns like context bundling, decision provenance, code as truth, and agent visibility. She demonstrates an engineering harness built on a knowledge graph designed to optimize token usage, streamline feedback loops, and maintain system reliability. This shift emphasizes to computing and information systems faculty the necessity of combining semantic data modeling with software engineering discipline to achieve auditability and consistency in autonomous AI systems.

THE TEACHING ANGLE
Students can evaluate the tension between relying solely on expanding LLM context windows versus implementing structured knowledge graphs to achieve repeatable decision-making and cross-domain traceability.

Read the original at infoq.com   Generate teaching or study materials

Instructors get discussion guides, assignments, and mini-cases. Students and readers get a plain summary, class prep, and an exercise. All built from the full article. Three are free with an account.

More in Computer Science