Journal · 03 / Research
Reality Runtime
Semantic runtime, agent execution, permission boundaries and open agent networks.
- Why Agents Need Verifiable StateFrom procurement questionnaires to external AI inquiries: why agents need attributable, current, permission-aware state — and what cryptography alone cannot prove.
- Reality Needs a Type SystemCan real-world claims be compiled into representations with machine-checkable constraints before anyone accepts or acts on them? An engineering note on subjects, scope, time, authority and evidence as types.
Forthcoming in this category
- 01The Agentic Web Needs Portable Facts, Not Another Walled Garden Forthcoming
- 02Who Is Responsible When an AI Agent Acts? Forthcoming
- 03From Agent Traces to Shared Facts Forthcoming