# Agentic AI drafts at the IETF: digest (since 7d) Last scan 2026-10-06 06:17 UTC: 104 drafts read, 0 classified, classifier typesafe/jev. Candidates waiting for review: 65. ## New candidates (25) - **draft-fane-opena2a-aip** rev -03 (2026-10-02): OpenA2A Agent Identity Protocol (AIP) Section: Identity and Authentication (100%). Relevance 97%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-fane-opena2a-aip/ - **draft-fane-opena2a-aap** rev -02 (2026-10-02): OpenA2A Agent Authorization Protocol (AAP) Section: Authorization and Delegation (100%). Relevance 96%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-fane-opena2a-aap/ - **draft-sharif-x509-agent-identity-profile** rev -04 (2026-10-02): X.509 Certificate Profile for Autonomous AI Agent Identity Section: Identity and Authentication (100%). Relevance 95%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-sharif-x509-agent-identity-profile/ - **draft-embesozzi-oauth-agent-native-authorization** rev -00 (2026-10-05): OAuth 2.0 Agents Native Authorization via Structured Elicitation Section: Authorization and Delegation (100%). Relevance 94%, agents primary subject. Style: clear, AI 25%. https://datatracker.ietf.org/doc/draft-embesozzi-oauth-agent-native-authorization/ - **draft-wei-aic-identity-cert** rev -02 (2026-10-02): AI Agent Identity Certificate (AIC) Extension for X.509 v3 Section: Identity and Authentication (99%). Relevance 94%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-wei-aic-identity-cert/ - **draft-das-protocols-enterprise-ai** rev -02 (2026-09-29): Assume the AI Server Is Already Compromised: Execution-Consequence Decoupling So a High-Risk Enterprise AI Cannot Join, Infer, or Send Section: Authorization and Delegation (64%). Relevance 94%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-das-protocols-enterprise-ai/ - **draft-das-agentic-tool-binding** rev -03 (2026-09-29): tool_use Is Not invoke(): Binding Execution-Finality to Agentic Tool-Call Interfaces and MCP Section: Authorization and Delegation (92%). Relevance 94%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-das-agentic-tool-binding/ - **draft-levi-agent-certification** rev -00 (2026-10-04): Autonomous Agent Certification Protocol (AACP) Section: Attestation and Trust (100%). Relevance 93%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-levi-agent-certification/ - **draft-wei-aic-jwt** rev -02 (2026-10-02): AI Agent Identity Certificate (AIC) JSON Web Token Profile Section: Identity and Authentication (71%). Relevance 93%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-wei-aic-jwt/ - **draft-nirvanai-nbtp-behavioral-trust** rev -01 (2026-10-01): NirvanAI Behavioral Trust Protocol (NBTP) Section: Attestation and Trust (100%). Relevance 93%, agents primary subject. Style: clear, AI 22%. https://datatracker.ietf.org/doc/draft-nirvanai-nbtp-behavioral-trust/ - **draft-das-execution-finality-enforcement-profiles** rev -02 (2026-09-29): Execution Finality at External-Effect Boundaries: Enforcement Profiles for 6G, AI-Native RAN, RF, ISAC, Accelerated Compute, Devices, and Autonomous Systems Section: Authorization and Delegation (69%). Relevance 93%, agents significant use case. Style: not scored. https://datatracker.ietf.org/doc/draft-das-execution-finality-enforcement-profiles/ - **draft-zambo-aer1** rev -11 (2026-10-05): AER-1: A Portable Execution Receipt for AI Agent Tool Calls Section: Attestation and Trust (100%). Relevance 92%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-zambo-aer1/ - **draft-gilda-wimse-agent-audit-record** rev -02 (2026-10-05): An Audit Record Format for AI Agent Authorization Decisions Section: Attestation and Trust (60%). Relevance 92%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-gilda-wimse-agent-audit-record/ - **draft-anandakrishnan-rats-ptv-agent-identity** rev -01 (2026-09-29): The Prove-Transform-Verify (PTV) Protocol for Attested Agent Identity Section: Attestation and Trust (90%). Relevance 92%, agents primary subject. Style: clear, AI 26%. https://datatracker.ietf.org/doc/draft-anandakrishnan-rats-ptv-agent-identity/ - **draft-das-execution-finality-protocol-layer** rev -01 (2026-09-29): The Missing Protocol Layer for the Agentic Internet: Computation Is Not Authority Section: Authorization and Delegation (90%). Relevance 92%, agents significant use case. Style: not scored. https://datatracker.ietf.org/doc/draft-das-execution-finality-protocol-layer/ - **draft-das-agentic-effectuation-boundary** rev -00 (2026-09-29): When AI Agents Hold the Keys: Threat Model and Execution-Finality Requirements for Autonomous High-Consequence Systems Section: Authorization and Delegation (83%). Relevance 92%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-das-agentic-effectuation-boundary/ - **draft-pidlisnyi-aps** rev -04 (2026-09-28): Agent Passport System (APS): Verifiable Authority, Lifecycle, Enforcement, and Evidence for AI Agents Section: Authorization and Delegation (88%). Relevance 92%, agents primary subject. Style: review, AI 28%. https://datatracker.ietf.org/doc/draft-pidlisnyi-aps/ - **draft-arsentev-llm-context-discovery** rev -01 (2026-10-05): Discovery and Retrieval of Publisher-Curated Context Files for Large Language Model Consumers Section: Agent Discovery and Naming (94%). Relevance 91%, agents significant use case. Style: not scored. https://datatracker.ietf.org/doc/draft-arsentev-llm-context-discovery/ - **draft-krausz-verification-state** rev -03 (2026-10-01): The verification.* Constraint Family: Pre-Action Fail-Closed Gates for AI Agent Decisions Section: Attestation and Trust (100%). Relevance 91%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-krausz-verification-state/ - **draft-das-rats-attestation-bnd-execution-finality** rev -04 (2026-09-29): Attestation-Bound Execution Finality for GPU, AI Accelerator, DPU, SmartNIC, and Confidential-Computing Infrastructure Section: Attestation and Trust (94%). Relevance 91%, agents significant use case. Style: not scored. https://datatracker.ietf.org/doc/draft-das-rats-attestation-bnd-execution-finality/ - **draft-das-agentic-adaptive-authorization** rev -00 (2026-09-29): Adaptive Authorization for Agentic AI: Graduated and Escalated Execution Control for Critical Infrastructure Section: Authorization and Delegation (100%). Relevance 91%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-das-agentic-adaptive-authorization/ - **draft-sharif-agent-audit-trail** rev -06 (2026-09-29): Agent Audit Trail: A Standard Logging Format for Autonomous AI Systems Section: Attestation and Trust (97%). Relevance 91%, agents primary subject. Style: clear, AI 22%. https://datatracker.ietf.org/doc/draft-sharif-agent-audit-trail/ - **draft-das-enterprise-ai-output-finality** rev -03 (2026-09-29): The Missing Piece for High-Value Confidential Enterprise AI: Non-Joinable Vaults and Output-Release Finality for Banking, Defence, and Public-Sector Deployments Section: Authorization and Delegation (89%). Relevance 90%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-das-enterprise-ai-output-finality/ - **draft-alla-agent-identity-document** rev -00 (2026-10-05): The Agent Identity Document: A Hosted, Accountable Public Record for AI Agents Section: Identity and Authentication (98%). Relevance 89%, agents primary subject. Style: not scored. https://datatracker.ietf.org/doc/draft-alla-agent-identity-document/ - **draft-morrison-org-alter-policy-provision** rev -04 (2026-09-30): Policy Provision and Governance Inheritance from an Organisational Identity Substrate Section: Authorization and Delegation (40%). Relevance 89%, agents primary subject. Style: clear, AI 15%. https://datatracker.ietf.org/doc/draft-morrison-org-alter-policy-provision/ ## Curated drafts that changed (3) - draft-beyer-agent-identity-problem-statement: expired (2026-10-03) https://datatracker.ietf.org/doc/draft-beyer-agent-identity-problem-statement/ - draft-beyer-agent-identity-architecture: expired (2026-10-03) https://datatracker.ietf.org/doc/draft-beyer-agent-identity-architecture/ - draft-bernardos-nmrg-agentic-network-optimization: new revision -01 → -02 (2026-10-02) https://datatracker.ietf.org/doc/draft-bernardos-nmrg-agentic-network-optimization/ Source: https://ietf.jaime.win/agentic-ai-new. JSON: https://ietf.jaime.win/api/agentic/digest?since=7d.