Why now – Palantir alternatives for Europe: what 'sovereign' actually means, and how European public bodies are decidingRegister →
Back to all webinars
webinarfreeonline

How – Inside the AI OS: running governed agents on your own cluster, live

Part 2 of the Sovereign AI series, for engineers and architects. No slides after minute five: an agent gets an identity and scoped permissions, calls tools over governed MCP, retrieves from the ontology rather than raw tables, runs inside the sandbox and is stopped when it steps outside policy, and everything lands in the audit trail — then the same stack brought up on a disconnected network. Properties and refusals, shown rather than claimed.

Speaking:
Xavier GeerinckPing Xavier

Language: English

RegisterPre-read: The Harness Holds
Agenda
11:00 - Where copilots stop and an AI OS starts (for the managers in the room)
11:05 - An agent gets an identity: scoped permissions, agent-to-agent auth
11:12 - Tools over governed MCP; retrieval from the ontology, not the tables
11:22 - The sandbox: what happens when an agent steps outside policy
11:30 - Audit and observability: the evidence a reviewer will ask for
11:36 - Finale: the same stack on a disconnected network — what changes
11:42 - Q&A

Ready to join?

Register