White paper · 17 pagesBuilding Secure Agents at Scalekyvvu
White paper · 17 pages
Building Secure Agents at Scale
A slightly weird white paper on agent security: what AI agents are, what makes them dangerous, and the full menu of ways to secure them.
What's inside
- 01What agents are, where they came from and what they're used for
- 02The individual action: an old problem with old controls
- 03The content: what guardrails are for
- 04The path: the danger agents genuinely add
- 05How agents are built: model, harness, tools and trust boundaries
- 06Isolation, access control, prompts, gateways, guardrails and runtime enforcement compared
- 07Why governance mostly follows from securing agents properly
Written by Prof. dr. Maurits Kaptein (CTO, Kyvvu), with feedback from Jeroen Janssen (Belastingdienst), Andriy Podstavnychy (Arcadis), Bart Jansen (ING), Rob Guikers (Rabobank), Niels Tailleur (Datashift) and Koko Visser (Valcon).