Protocol specification details a cryptographic evidence lifecycle for AI agent runtimes, indicating improved auditability and policy enforcement across autonomous agent interactions.
CCS defines the evidence protocol for the agent runtime protocol stack. It specifies the complete evidence lifecycle: intake, generation, standardization, propagation, and enforcement consumption. CCS occupies the position between Transport (MCP/A2A) and Enforcement (AEB), responsible exclusively for evidence generation, standardization, cross-agent propagation, and delivery to enforcement consumers. CCS produces a tamper-evident, cryptographically bound artifact — a CCS Receipt — for every tool invocation decision made by an agent runtime's governance layer. This is version -05, submitted to the IETF as Internet-Draft draft-correctover-ccs-05 on 20 August 2026 (Submission #167891), 64 pages, 18,574 words. Supersedes version -04 (DOI: 10.5281/zenodo.21915312).
No takes yet. Share an insight, caveat, or question.
Guigui Wang (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: