In this SHI Fall Summit interview, theCUBE’s Paul Gillin sits down with Luke Norris, co-founder and chief executive officer of Kamiwaza, to unpack how agentic AI is moving from theory to production inside large enterprises and government. Norris outlines Kamiwaza’s horizontal AI orchestration engine – built on an “inference mesh,” a distributed data engine with an enterprise-wide metadata catalog and a relationship-based authentication control that preserves user permissions across chained agents. The discussion dives into real security implications such as the mosaic effect, where AI can surface sensitive insights by correlating previously unconnected datasets. Norris also shares the team’s focus on Section 508 accessibility compliance and why it matters now as states tighten requirements and funding is tied to adherence. Norris details ARIA, a multi-agent solution developed with HPE and delivered by SHI, that automates 508 remediation end-to-end. A computer-use agent, a large language model and a visual model work in concert to understand pages, PDFs and charts, then apply compliant metadata and update HTML for accessibility – followed by a verification pass against evolving federal and state rules. He explains how this “wedge solution” gives agencies a fast, ROI-focused onramp to agentic AI: packaged deployment within days and typically achieving full website remediation within a week – versus multi-year manual efforts. The conversation closes with how Kamiwaza flexibly integrates commercial and open-weight models on its orchestration platform and how insights captured through ARIA can seed broader secure AI initiatives across the enterprise.