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

8.2 relevance

Directly addresses agentic AI architectures with knowledge graphs, highly technical and actionable for AI orchestration interests.

AI/ML infoq.com

Answer the board on AI readiness

Arrive with evidence, not opinion. See how your foundation benchmarks against your peers, get a clear read, and leave with a ranked place to start.

Why It Matters

For a solutions architect building agent orchestration systems, knowledge graphs provide a foundation for managing context, verifying agent decisions, and reducing token overhead — directly addressing reliability and cost challenges in production.

Key Takeaways

Implement knowledge graphs as your agentic system's backbone to gain traceability, control token waste, and enable code-driven truth for deterministic agent behavior.

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

Summary

Cassie Shum presents four architectural patterns for production agentic AI systems using knowledge graphs: context bundling, decision provenance, code as truth, and agent visibility. She demonstrates an engineering harness built on RelationalAI's knowledge graph that optimizes token usage and closes feedback loops for agentic workflows, moving beyond basic RAG to enable reasoning.

Author

Cassie Shum