{"id":3,"date":"2026-04-05T03:41:47","date_gmt":"2026-04-05T03:41:47","guid":{"rendered":"https:\/\/www.w3.org\/community\/aivs\/2026\/04\/05\/call-for-participation-in-agentic-integrity-verification-specification-community-group\/"},"modified":"2026-04-05T03:41:47","modified_gmt":"2026-04-05T03:41:47","slug":"call-for-participation-in-agentic-integrity-verification-specification-community-group","status":"publish","type":"post","link":"https:\/\/www.w3.org\/community\/aivs\/2026\/04\/05\/call-for-participation-in-agentic-integrity-verification-specification-community-group\/","title":{"rendered":"Call for Participation in Agentic Integrity Verification Specification Community Group"},"content":{"rendered":"\n<p>The <a href=\"https:\/\/www.w3.org\/community\/aivs\/\">Agentic Integrity Verification Specification Community Group<\/a> has been launched:<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-dots\"\/>\n\n\n\n<p>AI agents increasingly perform consequential actions on behalf of humans \u2014browsing websites, submitting forms,  executing code, and making purchasing decisions. When things go wrong (an agent takes an unintended action, produces an incorrect output, or is used in a regulated context), there is currently no agreed upon way to prove what the agent actually did, in what sequence, and whether the record has been tampered with. Existing observability tools (such as OpenTelemetry and LangSmith) log agent behavior but provide no cryptographic guarantees of completeness or authenticity.<\/p>\n\n<p>Regulatory frameworks are beginning to require audit trails for AI systems (EU AI Act Article 19, ISO\/IEC 42001, NIST AI RMF), but none prescribe a format. This group will explore open formats for cryptographic proof of AI agent sessions \u2014portable, self-verifiable records that any party can verify independently, without network access or external infrastructure.<\/p>\n\n<p>The <a href=\"https:\/\/github.com\/bkauto3\/Conduit\/blob\/main\/spec\/AIVS.md\" target=\"_blank\" rel=\"nofollow\">Agentic Integrity Verification Specification (AIVS) v1.0<\/a> is intended to serve as a starting point for discussion within the group, but is not intended to constrain the group&#8217;s discussions or decisions about future deliverables.<\/p>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-dots\"\/>\n\n\n\n<p>In order to <a href=\"\/community\/aivs\/join\">join the group<\/a>, you will need\n    a <a\n            href=\"\/account\/request\/\">W3C account<\/a>. Please note, however, that <a\n            href=\"\/community\/about\/faq\/#is-w3c-membership-required-to-participate-in-a-community-or-business-group\" target=\"_blank\" rel=\"nofollow\">W3C\n        Membership<\/a> is not required to join a Community Group.<\/p>\n\n\n\n<p>This is a community initiative. This group was originally proposed on 2026-03-14 by\n    Ben Stone. The following people supported its creation: Ruoxi Ran, Ben Stone, Robert Douglas Muncaster, Khushboo Parmar and Erik Delgado.\n    W3C&#8217;s hosting of this group does not imply endorsement of the activities.<\/p>\n\n\n\n<p>The group must now <a href=\"\/community\/about\/faq\/#how-do-we-choose-a-chair\" target=\"_blank\" rel=\"nofollow\">choose a chair<\/a>. Read more about <a\n            href=\"\/community\/about\/faq\/#how-do-we-get-started-in-a-new-group\" target=\"_blank\" rel=\"nofollow\">how to get started in a new group<\/a> and\n    <a href=\"\/community\/about\/good-practice-for-running-a-group\/\">good practice for running a group<\/a>.<\/p>\n\n\n\n<p>We invite you to share news of this new group on social media and other channels.<\/p>\n\n\n\n<p>If you believe that there is an issue with this group that requires the attention of the W3C staff, please email us\n    at <a href=\"mailto:site-comments@w3.org\" target=\"_blank\" rel=\"nofollow\">site-comments@w3.org<\/a><\/p>\n\n\n\n<p>Thank you,<br\/>\nW3C Community Development Team<\/p>\n\n","protected":false},"excerpt":{"rendered":"<p>The Agentic Integrity Verification Specification Community Group has been launched: AI agents increasingly perform consequential actions on behalf of humans \u2014browsing websites, submitting forms, executing code, and making purchasing decisions. When things go wrong (an agent takes an unintended action, &hellip; <a href=\"https:\/\/www.w3.org\/community\/aivs\/2026\/04\/05\/call-for-participation-in-agentic-integrity-verification-specification-community-group\/\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":24181,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_s2mail":"","footnotes":""},"categories":[2],"tags":[],"class_list":["post-3","post","type-post","status-publish","format-standard","hentry","category-announcements"],"_links":{"self":[{"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/posts\/3","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/users\/24181"}],"replies":[{"embeddable":true,"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/comments?post=3"}],"version-history":[{"count":0,"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/posts\/3\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/media?parent=3"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/categories?post=3"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.w3.org\/community\/aivs\/wp-json\/wp\/v2\/tags?post=3"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}