AgentsSeptember 12, 2026via InfoQ AI/ML
Presentation: From Retrieval to Reasoning: Building Production-Ready Agentic AI Systems with Knowledge Graphs
Why it matters
Practitioners building agentic systems need patterns for reliability, observability, and cost control. Knowledge graphs as infrastructure for agent feedback loops and decision tracing move agents from prototype to production.
Key signals
- 4 architectural patterns: context bundling, decision provenance, code as truth, agent visibility
- Knowledge graphs as foundation for agentic systems
- Engineering harness for feedback loops and token optimization
- Focus on system reliability and observability in production agents
- Speaker: Cassie Shum
- Source: InfoQ presentation (vendor/conference content)
- Knowledge graphs positioned as critical foundation for agentic systems (not just RAG enhancement)
- Focus on feedback loops, token optimization, and system reliability—production engineering concerns
- Engineering harness approach suggests deployment-ready tooling
The hook
Beyond RAG: 4 architectural patterns for production-ready agents, from decision provenance to token optimization.
Cassie Shum discusses why knowledge graphs serve as a critical foundation for agentic systems. Moving beyond basic RAG, she explains 4 practical architectural patterns: context bundling, decision provenance, code as truth, and agent visibility. She demonstrates an engineering harness built on a know…