A deep dive into practical strategies for improving AI reasoning in code and structured tasks. The talk covers capturing richer user intent through examples, enabling collaborative interaction, and using automated inspection for iterative refinement, illustrated with real-world applications from Microsoft.
Matthew Glickman, CEO of Genesis Computing, discusses the rise of AI data agents designed to automate complex data engineering workflows. He covers the "last 10%" problem in enterprise AI, the unique value of targeting the data engineer persona, and how these agents can tackle challenges like legacy system migration and knowledge capture, ultimately giving valuable time back to data teams.
Sam Partee, CTO of Arcade AI, explains that building production-grade agentic systems requires moving beyond simple chatbots. He details the critical components for creating reliable, secure, and scalable tools, including rigorous schema management, the principle of least privilege, continuous evaluation, and a crucial distinction between 'exploratory' and 'operational' tools.
Sumeet Jeswani of Google discusses the critical shift from AI-powered to AI-orchestrated cyber attacks, where autonomous agents now lead complex security breaches. The summary explores new manipulation techniques like prompt and data injection, and outlines a multi-layered defense strategy rooted in the principles of least agency, defense-in-depth, and building security into AI systems from the ground up.
Joe Reis and Matt Housley, authors of "Fundamentals of Data Engineering," discuss how AI has transformed data engineering practices since their book's release. They emphasize the enduring importance of foundational knowledge, the challenges AI poses for junior engineers, and the critical balance between leveraging AI assistance and maintaining core expertise in an increasingly complex field.
Edwin Chen, founder and CEO of Surge AI, discusses his contrarian, bootstrapped approach to building a billion-dollar company, the critical role of high-quality data and 'taste' in training advanced AI models, the pitfalls of current benchmarks, and why Reinforcement Learning environments are the next frontier in AI.