Agentic AI Is Forcing Procurement to Rethink What It Means to Trust a Vendor

The rise of agentic AI systems is fundamentally altering the nature of vendor relationships, moving beyond traditional counterparty models where vendors are singular, known organizations. This article explores how AI-mediated workflows create porous organizational boundaries, with vendors' autonomous systems often invoking other undisclosed third-party systems. This shift introduces new risks and failure modes, including counterparty drift, cross-organizational hallucinations, fragmented audit trails, and reviewer fatigue. We argue that existing procurement and third-party risk management frameworks are insufficient for this new reality. Drawing on emerging best practices and converging regulatory trends (e.g., DORA, EU AI Act), the article proposes revisions to governance practices. These include mandating disclosure of autonomous system chains, negotiating cross-organizational audit trail access, and explicitly defining human override and accountability points. The article concludes by highlighting unresolved challenges in cross-organizational liability, trust frameworks for machine-speed coordination, and vendor concentration risk, urging procurement and risk leaders to adapt their strategies for an era of networked autonomous systems.

• Machine Intelligence