{
  "id": 12641046,
  "title": "AI in Production: What Breaks, What Works, and Who Approves It? | InfoQ Webinar",
  "url": "https://urgent.news/2026/10/07/ai-in-production-what-breaks-what-works-and-who-approves-it-infoq",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-07T14:00:00.000Z",
  "source": {
    "name": "InfoQ",
    "slug": "infoq",
    "url": "https://www.infoq.com/news/2026/10/infoq-ai-webinar/"
  },
  "original_language": "en",
  "account": "InfoQ is hosting an AI-focused webinar titled \"AI in Production: What Breaks, What Works, and Who Approves It?\" on October 14. The 60-minute live panel discussion will feature five practitioners with experience building, securing, and operating AI systems in production environments. These experts will share their insights on the challenges and risks that arise when AI systems go beyond individual developer machines and into CI pipelines, RAG (retrieval-augmented generation) pipelines, and across systems with different permissions and failure modes.\n\nThe panel will explore the tension between the desire for agents to move faster and do more, versus the need for tighter limits on what those agents can see and touch from a privacy and security perspective. They will discuss how teams draw the lines for autonomy and the consequences of granting too much or imposing insufficient controls.\n\nKey topics for discussion include:\n- How teams handle sensitive or outdated data in RAG pipelines\n- Verification methods for AI-generated changes before they enter delivery workflows\n- Permissions, review gates, and governance decisions for coding agents across the software delivery lifecycle\n- Making retrieval reliable in production AI systems built on large document repositories\n- Experiences from building generative AI products and production data and machine-learning pipelines\n\nThe panelists come from diverse backgrounds:\n- Hien Luu, chair of QCon AI New York 2026, with experience leading machine-learning platform teams and authoring MLOps with Ray.\n- Katharine Jarmul, a privacy and security specialist in machine learning and AI systems, and author of Practical Data Privacy.\n- Zichuan Xiong, a Principal at Thoughtworks, co-facilitator of the InfoQ Certified AI-Assisted Engineering Program.\n- Premanand Chandrasekaran, a Market Tech Director at Thoughtworks with 30+ years of software team leadership experience.\n- Lan Chu, an AI Tech Lead and Senior Data Scientist with experience in production AI systems and generative AI products.\n\nAttendees who register will receive the webinar recording, which they can watch later. The webinar is free to register for and open to all engineers, platform teams, and security professionals interested in learning about the practical aspects of deploying AI systems in production environments.",
  "summary": "On October 14, InfoQ hosts a free 60-minute panel with five practitioners on running AI in production. They'll discuss agent autonomy and human approval, how to verify AI-generated changes, sensitive-data exposure, and production RAG. Registrants can submit questions and will receive the recording. 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."
}