InfoQ - QCon AI 2025

Presentation: AI Works, Pull Requests Don’t: How AI Is Breaking the SDLC and What To Do About It

Michael Webster — Fri, 26 Jun 2026 14:17:00 GMT

Michael Webster discusses the rise of headless AI agents and their impact on software delivery pipelines. He shares how massive, AI-generated pull requests create a severe bottleneck for human reviewers and introduce persistent technical debt. Learn how engineering leaders can leverage test impact analysis and automated validation pipelines to verify agentic output without sacrificing stability.

By Michael Webster

Presentation: Rules for Understanding Language Models

Naomi Saphra — Wed, 24 Jun 2026 11:25:00 GMT

Naomi Saphra discusses 5 rules governing language model behavior, breaking down why LLMs act like populations rather than individuals. She explains how tokenization creates strange semantic blind spots and highlights the mechanics of sycophancy, showing how models leverage subtle data associations to match user biases and demographics - even guessing political views based on favorite sports teams.

By Naomi Saphra

Presentation: AI Agents to Make Sense of Data at OpenAI

Bonnie Xu — Fri, 19 Jun 2026 12:02:00 GMT

OpenAI’s Bonnie Xu discusses Kepler, an internal AI data analyst agent built to query 600+ petabytes of data. She explains how they overcome context window limits using MCP, automated code crawling, and RAG. Xu also shares how their team leverages scoped semantic memory for self-learning and utilizes AST-based LLM grading to build a robust, regression-free evaluation pipeline.

By Bonnie Xu

Presentation: From Hype to Strong Foundations: What the Rise, Fall and Resurgence of Agents Can Teach Us about Outlasting the Cycle

Aditya Kumarakrishnan — Wed, 17 Jun 2026 11:04:00 GMT

Aditya Kumarakrishnan explains how to move past the "amnesia phase" of AI. He shares a blueprint for engineering leaders to build modular agent frameworks using CoALA, leverage decades of process science for scalable workflows, and "terraform" legacy environments into robust, event-sourced artifacts capable of handling unpredictable, cross-functional agent demands.

By Aditya Kumarakrishnan