//pragmatic leaders

signal

Datris put agent identity and scoped permissions at the core of AI data control

Builders moving AI agents from pilot to production must treat agents as scoped identities with fine-grained permissions and auditability to maintain control and accountability over data access and code execution.

Frame 1 of 4

Datris adds scoped identity and per-action policy to AI data control plane

Datris released an open-source data control plane for AI agents that includes credential brokering, isolated script execution, per-action policy, audit logging, row-level provenance, and automated recovery. Each agent connects with its own key and is limited to permitted tools and actions, enabling secure, accountable AI data operations in production.