PIES approaches this at three levels:
- Building apps – AI-assisted generation, governed by policy, accelerates the creation of workflow applications.
- Running agents – every deployed app has an auto-generated MCP server. Agents can call any function, query any data model, and trigger any workflow, inheriting the app’s RBAC so agents only do what the user could do.
- Embedding AI – each application ships with its own in-app AI tuned to that domain, routing through the same governance layer.
The governance layer is the linchpin every agent call is policy-routed, optionally redacted, and fully audited.
Add Comment