Securing AI Agents: Identity, Authorisation, and the DPACT Framework

Why watch

Sahil Agarwal explains the DPACT framework (Delegation, Policy, Auditability, Context, Time) as a blueprint for securing AI agents, addressing the shift from simple token-based access to bounded, delegated authority. The interview targets software architects and senior engineers building responsible, guardrailled agentic systems who need to understand identity and authorization patterns for AI deployments.