AI
- Human-in-the-loop AI agents: what approval has to mean: An agent that asks before it acts is only safe if the asking is enforced by the platform, not by the prompt. (2026-11-12)
- Cloud models, governed: Role-based model selection, zero data retention by default, and local models for air-gapped sites. (2026-10-30)
- Deterministic by design: the Agent Stack: Sessions as event logs, a pure handler, explicit effects, and a person in front of every write. (2026-10-29)
- Introducing Converge: An ontology-centred platform where data, applications and AI share one governed model. (2026-10-28)