AI Con USA 2026 - Architecture - Design
Customize your AI Con USA 2026 experience with sessions covering architecture and design.
Monday, June 8
Human in the Loop
New"We love AI and use it for everything we do!" "We hate AI and will NEVER use it for anything ever, I swear to god!" Which camp are you in? This will be a question that will come up over and over in 2026 and beyond. If you use AI for EVERYTHING and think you can be mistaken for AI…has AI not already taken your job? We all need to get INTENTIONAL about our stance in the AI-verse. Have you thought deeply about what is a good activity for AI to lead on and what should be uniquely human? We are already seeing a premium price tag on in-person, uniquely human-to-human experiences, and this will...
AI Governance as Code: An Introduction to AIGovOps
NewAI governance is no longer optional. Like privacy and security before it, governance is quickly becoming a production requirement, enforced through regulation, audits, and fines—often after real harm has already occurred. Ken Johnston and Bob Rapp, founders of the AiGovOps Foundation, introduce AIGovOps: the practice of implementing AI Governance as Code, embedded directly into delivery pipelines and operational workflows. This hands-on session begins with a concise review of Responsible AI and the NIST AI Risk Management Framework, followed by an interactive HARMS workshop using real AI...
Become an AI Power User
Impostering a bit in the AI-verse? Overwhelmed by daily AI announcements? Unsure you're using AI most effectively? Tiny bit of FOMO? We've got you covered! In this workshop, we'll help you become an AI Power User. Become a boss at your job, whatever your role or industry! We'll show you where AI shines and where you'll want to be careful, plus toss you lots of hands-on practice. In our time together, we'll help you pinpoint YOUR niche, build a custom AI assistant, and develop a comms strategy to show off your new skills. You'll walk out with cutting-edge knowledge, a prompt library...
Build Your Own AI News Agent with Redis + LangGraph.js.
NewTired of sifting through endless news sources and missing the topics you care about? This hands-on workshop empowers you to build a personalized AI news assistant using Redis and LangGraph.js. You’ll learn to ingest articles from RSS feeds, summarize and analyze them, extract structured data, and generate embeddings—all stored in Redis for powerful hybrid (vector + structured) search. Your agent will provide a web interface for browsing and semantic search, and even chat with you about current events, retrieving relevant articles and metadata using RAG techniques. LangGraph.js orchestrates...
Tuesday, June 9
Agentic AI: From Rules to Reasoning
NewAI 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...
Wednesday, June 10
Will the Real Autonomous Agent Please Stand Up: What’s Real, What’s Not, and What You Actually SHOULD Be Investing in in the AI-Verse
If you’ve seen the news lately, the tech bros will have you believe that AI is both here to take your job and also your soul. On the other side, people are saying that we are in an AI-bubble, it’s all hype, and we don’t need to worry about it at all. Which is it? The truth is…it’s a little of BOTH. Dona will demystify what the latest buzzwords in AI (what is OpenClaw all about) and show you a roadmap for how you can AND SHOULD be using AI in your day-to-day life. You’ll learn how to set up an experiment framework for yourself, identify the workflows AI is actually good for, how to run the...
AI-Native Delivery: Why the Future Belongs to Those Who Specify and Validate
AI in software delivery is no longer just about experimenting with copilots or generating code faster. It is about changing how software is imagined, specified, generated, validated, governed, and improved. As AI continues to be used for producing prototypes, requirements, code, tests, documentation, deployment artifacts, and operational insights, the software lifecycle shifts from a sequence of handoffs into a continuous learning loop. The real opportunity is therefore not only about leveraging AI tools, but adopting a new working model for transforming intent into trusted outcomes. Join...
Containers That Think: Building AI-Powered Self-Healing Applications That Never Go Down
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...
Revolutionizing Healthcare with AI
Agentic AI at the Edge: Building Mobile AI Agents for Automotive & MedTech
Shipping AI into regulated, safety-critical mobile apps is more than “just call an LLM.” In automotive and medical contexts, we must meet strict privacy, latency, and auditability requirements while working with flaky connectivity and device constraints. In this talk, Ronak will share a field-tested architecture for agentic AI on the edge: a hybrid edge–cloud agent that uses tool-calling plugins, a policy engine for pre/post-prompt guardrails, offline fallbacks, and structured telemetry for audits. He will walk through how his team bounds agent behavior with capability cards, redacts PHI/...
Unlock Exponential Productivity: The AI Maturity Model for Product Engineering
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...
Show Me the ROI: What Enterprise AI Actually Delivers in Year 4 - Panel
The hype cycle is over. The pilot graveyard is full. MIT research suggests that 95% of Generative AI implementations have little to no measurable impact on P&L. So what separates the 5% that actually deliver? In this no-fluff panel, practitioners from the front lines of enterprise AI — spanning automotive, cloud platforms, and the messy middle of real-world deployment — will have a candid conversation about what's working, what consistently stalls, and what it actually takes to move from experimentation to results.
The panel will discuss:
The use cases that outperform the hype...Thursday, June 11
Building Agentic Engineering Teams
Agentic engineering has quietly inverted the fundamental bottleneck of software development. For decades, the hard part was building, so we optimized teams for execution speed, hired specialists to cover capability gaps, and treated wasted work as a cost to be managed through careful planning and consensus. Now an engineer with the right tools can scaffold major features in hours, often faster than they can get a meeting on the calendar to discuss it. This talk is a field guide for leading teams through that inversion. It reexamines the hiring calculus, what makes an early career engineer...
Engineering AI Infrastructure for Efficient Inference at Scale
As AI models grow in complexity and scale, inference efficiency has emerged as a critical engineering challenge for enterprise deployment. Traditional infrastructure built for training workloads often fails to meet the latency, throughput, and cost demands of large-scale inference operations. In this session, Sandeep will be sharing practical insights from engineering AI infrastructure at Broadcom, focusing on the end-to-end optimization of compute, networking, and storage subsystems. The talk explores techniques such as dynamic workload placement, adaptive batching, model quantization,...