Haytham Abuelfutuh, CTO of Union.ai, argues that the key to production-ready AI agents is not preventing failure, but embracing it. He introduces the '3 D's' framework—Dynamic, Durable, and Defended—for building agents that can fail cheaply and recover automatically, grounded in a real-world case study of an agent system indexing over 250,000 products on Flyte.
Explore GPT-Realtime-2, OpenAI's advanced voice AI model, through practical demos and a deep dive with Sierra on building production-grade, low-latency voice agents with complex reasoning and tool use.
A product engineer from Granola shares a candid account of the challenges in moving AI features from the playground to production. This talk covers the pitfalls of "one-shot" solutions like web search and generic prompts, and details Granola's strategy of building custom internal tracing and development tooling to create a tight, effective feedback loop for iteration.
Agent failures are unlike traditional software failures. This workshop provides a practical framework for monitoring production agents, moving beyond evals to real-world observability by using explicit signals (errors, latency) and implicit signals (user frustration, refusals, self-diagnostics) to catch regressions and understand agent behavior.
Sandipan Bhaumik from Databricks explains that scaling from one to many AI agents is a distributed systems problem, not an AI one. He details common architectural anti-patterns like shared mutable state that cause race conditions and silent failures. The talk provides a practical framework based on distributed systems engineering, covering crucial patterns like choreography vs. orchestration, immutable state management with versioning, data contracts, and failure recovery using circuit breakers and compensation (Saga) patterns. Bhaumik illustrates how to build a robust, production-grade multi-agent architecture using tools like Databricks, LangGraph, and MLflow.
Learn practical strategies to adapt third-party MCP server tools for production AI applications. This talk covers five key practices: curating tools, enhancing descriptions, implementing deterministic guardrails, composing new tools from existing ones, and leveraging tools as simple functions, all demonstrated through a real-world "Spec Reviewer" example.