Room: Salon H AI models are getting tasked to do increasingly complex and industry specific tasks, where different retrieval approaches provide distinct advantages in accuracy, explainability, and cost to execute. GraphRAG retrieval models have become a powerful tool to solve domain-specific problems where answers require logical reasoning and correlation that can be aided by graph relationships and proximity algorithms. I will demonstrate how the agentic combination of RAG and GraphRAG retrieval patterns can improve analysis of dependency and security information to optimize a DevOps pipeline.