AI Con USA 2026 - AI & ML Productivity Tools

Tired of staring at the chat box of an AI assistant wishing it could actually do a task for you rather than just telling you what to do? Model Context Protocol (MCP) is the glue between an AI agent and your data and tools. With MCP, AI assistants can read your documents, conversations, and other context and take action for you by sending emails, submitting tickets and more. But what really is MCP and how do you use MCP servers safely in practice as part of your day-to-day workflow? This half-day course introduces MCP and dives into practical use cases. Laurel will walk you through how to...

Theory is great, but what about getting your hands dirty with some real problem-solving? Lets build your own AI Operating System that you'll take home and use immediately. Join Melissa Benua and Ryan Lee for a hands-on session where you'll construct a personalized AI toolkit that solves YOUR specific testing problems, regardless of your coding background. We'll start by deconstructing the modern software development lifecycle used by all tech companies to safely ship software solutions to their customers, and show you exactly where AI accelerates each phase. Then we'll prove a critical...

AI agents have existed for decades, but generative AI has fundamentally changed what agents can do and how they are designed and built. Come and explore the evolution of AI agents across two major waves. First, learn the foundations of Agentic AI through agents built using rules, heuristics, and traditional machine learning, examining where these approaches excel and why they struggle with complexity, ambiguity, and scale. Then dive into the second wave of agents powered by generative AI and multimodal large language models. These modern agents can reason, plan, use tools, and interact...

Enterprise containerized applications face a critical reliability crisis with complex failure modes including memory leaks, cascading failures, network partitions, and resource contention that traditional monitoring tools cannot predict or resolve fast enough. Organizations typically experience multiple production incidents monthly with multi-hour resolution times that consume significant engineering resources while causing customer-facing outages and revenue loss. Traditional approaches rely on reactive monitoring, manual troubleshooting across distributed container environments, and time...

Are you ready to transform your productivity from incremental gains to exponential growth? Whether you're an individual contributor or engineering leader, this session introduces the AI Maturity Model, a proven framework that guides technical teams through five distinct levels of AI adoption—from 33% productivity boosts to an extraordinary 1000% increase. Discover how to navigate each stage: Level 1 (Foundation, 33%) builds essential AI awareness; Level 2 (Literacy, 75%) develops practical AI skills; Level 3 (Fluency, 300%) masters AI-assisted workflows; Level 4 (Agents, 500%) implements...

We are entering a defining chapter for bioscience—one where AI is no longer an accessory, but a core engine of discovery. At the Allen Institute, AI is being woven throughout the scientific process empowering research teams to analyze complex biological systems at scale. Their teams are collaborating to develop frontier AI applications like advanced computer vision to interpret high-resolution imaging data, multimodal models that integrate complex molecular, cellular, and physiological signals, as well as intelligent systems to assist researchers as they navigate and synthesize vast...

There is no question that Generative AI models can improve the productivity of almost every role within the software development process. Tools like GitHub Copilot, Amazon CodeWhisperer, Tabnine, and more, can be critical tools to help developers do their jobs better and faster. Join Coveros CEO Jeffery Payne to explore how Generative AI solutions help software developers generate and supplement code and even suggest improvements to what you’ve already created.

The next generation of security automation isn’t found in a chat interface—it’s found in Agents. While basic AI assistants can provide security advice and even remediate vulnerabilities, the real breakthrough for security teams lies in using an Agentic Workflow for security testing: the ability to build, customize, and orchestrate specialized agents that take ownership of the testing and remediation lifecycle. In this session, Jeffery Payne demonstrates how to move beyond conversational AI to create autonomous security agents using standardized formats compatible across tools like GitHub...

Modern AI systems fail not only because of flawed models but because evaluation is often treated as a one-time task rather than an ongoing discipline. This session addresses the challenge of scaling evaluation across teams and pipelines to ensure model reliability, fairness, and performance. Drawing from real-world experience in large-scale financial analytics, Anusha Dwivedula will examine how product and data teams can collaborate to design a continuous evaluation framework that integrates precision, recall, and drift metrics with observability, lineage, and quality controls. She will...