{
  "id": 10992409,
  "title": "InfoQ Online Cohorts Address AI Security and Coding Agent Verification",
  "url": "https://urgent.news/2026/09/30/infoq-online-cohorts-address-ai-security-and-coding-agent-verification",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-30T17:00:00.000Z",
  "source": {
    "name": "InfoQ",
    "slug": "infoq",
    "url": "https://www.infoq.com/news/2026/09/onlinecohorts-ai-certifications/"
  },
  "original_language": "en",
  "account": "InfoQ is hosting two five-week online certification cohorts in October 2026, focusing on AI Security & Privacy Engineering and AI-Assisted Engineering. The AI Security & Privacy Engineering cohort, beginning October 26, aims to protect sensitive data and inspect security controls within AI systems. Meanwhile, the AI-Assisted Engineering cohort, starting October 19, centers on verifying coding agents that modify existing codebases.\n\nIn the AI Security & Privacy Engineering program, participants tackle their own work problems, mapping out the data flow and potential risks. They employ threat modeling, red teaming, and testing to identify vulnerabilities and determine who bears responsibility for the unaddressed risks. Katharine Jarmul, a prominent figure in data privacy and security, facilitates this cohort, employing a data-centric approach to AI security reviews.\n\nThe AI-Assisted Engineering cohort, led by Zichuan Xiong and Premanand Chandrasekaran, works on a shared codebase to build context around coding agents. They limit agent permissions, integrate tests and sensors, and separate generation from review. The cohort culminates in a capstone where participants share their harness and present a rule or agent skill, comparing their results with initial predictions. Both cohorts offer confidential peer groups, allowing participants to share experiences and insights with seasoned engineers under various constraints.",
  "summary": "A look at two InfoQ online certification cohorts covering security and privacy decisions in production AI systems and the verification needed when coding agents work in existing codebases. By Artenisa Chatziou",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}