{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"AI Transformation & Governance","title":"How to Control AI Agents with Constitutional AI | Interview with Bennett Borden","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/f9ea4699\"></iframe>","width":"100%","height":180,"duration":2721,"description":"In this episode of AI Transformation & Governance, host Dejan Kosutic speaks with Bennett Borden, who is the CEO, data scientist, and AI ethicist at Clarion AI Partners, and member of the NIST AI RMF Scientific Advisory Board. They talk about building and controlling AI agents through “constitutional AI” plus governance engineering. Borden explains defining agent personas and behavioral “thou shalts/shalt nots,” attaching scoring mechanisms to each principle, and, in sensitive use cases, adding a companion quality-control bot that reviews outputs and sends failures back for revision, producing telemetry and evidentiary artifacts for compliance. He discusses model selection trade-offs, risks of unethical optimization and agent deception, and emphasizes risk assessment, monitoring where AI “touches the world,” curated company data/RAG for accuracy, and combining deterministic methods with gen AI.\nLINK FROM THE VIDEO\n► ISO 42001 Courses https://advisera.co/Courses-ISO42001","thumbnail_url":"https://img.transistorcdn.com/0SL4mrgF4z2big65KaQ7Na4A9ZzmL7FfphAlTK44DEE/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9hYWE0/NzExMGY1MTRmNzAw/ZjZkMjgzZWQ3MGZj/ZWUxNS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}