{"id":1155394,"date":"2025-12-04T04:12:16","date_gmt":"2025-12-04T12:12:16","guid":{"rendered":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/?post_type=msr-project&p=1155394"},"modified":"2025-12-15T03:15:18","modified_gmt":"2025-12-15T11:15:18","slug":"towards-the-psychological-security-of-agentic-ai","status":"publish","type":"msr-project","link":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/project\/towards-the-psychological-security-of-agentic-ai\/","title":{"rendered":"Towards the Psychological Security of Agentic AI"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\"background\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

Towards the Psychological Security of Agentic AI<\/h1>\n\n\n\n

<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n

Towards The Psychological Security of Agentic AI<\/em><\/strong><\/p>\n\n\n\n

This project addresses the critical challenge of auditing psychological safety in agentic AI systems designed to deliver evidence-based interventions for mental and cognitive well-being. While agentic AI chatbots can emulate psychotherapeutic interventions and enable personalized support, they also pose risks to both patients and clinicians, including hallucinated advice, relational harms, and privacy breaches. This work will investigate clinician-informed \u201cpsychological safety red teaming\u201d methods and scalable interfaces to audit these AI technologies. We will investigate these methods and interfaces through the development of an AI chatbot designed to support individuals experiencing early cognitive decline. This project will result in principles and tools for safe, responsible deployment of agentic AI in high-stakes, emotionally sensitive contexts.<\/p>\n\n\n\n

This research is conducted via\u00a0The Agentic AI Research and Innovation\u00a0<\/a>(AARI) Initiative which focuses on the next frontier of agentic systems through\u00a0Grand Challenges<\/em>\u00a0with the academic community and Microsoft Research.<\/p>\n\n\n\n\n\n

<\/p>\n","protected":false},"excerpt":{"rendered":"

Towards The Psychological Security of Agentic AI This project addresses the critical challenge of auditing psychological safety in agentic AI systems designed to deliver evidence-based interventions for mental and cognitive well-being. While agentic AI chatbots can emulate psychotherapeutic interventions and enable personalized support, they also pose risks to both patients and clinicians, including hallucinated advice, […]<\/p>\n","protected":false},"featured_media":1155708,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-1155394","msr-project","type-msr-project","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"","related-publications":[],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"related-researchers":[{"type":"guest","display_name":"Dan Adler","user_id":1157414,"people_section":"Section name 0","alias":""},{"type":"guest","display_name":"Tanzeem Choudhury","user_id":1157413,"people_section":"Section name 0","alias":""},{"type":"guest","display_name":"Thalia Viranda","user_id":1157416,"people_section":"Section name 0","alias":""},{"type":"user_nicename","display_name":"Zilong Wang","user_id":43764,"people_section":"Section name 0","alias":"wangzilong"}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1155394","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":9,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1155394\/revisions"}],"predecessor-version":[{"id":1158522,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/1155394\/revisions\/1158522"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media\/1155708"}],"wp:attachment":[{"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=1155394"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=1155394"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=1155394"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=1155394"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/new-cm-edgedigital.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=1155394"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}