Architecture
Decision Models in Agentic Architectures: From Production to Agent Skills
Tuesday Jun 2 / 02:30PM EDT
In agentic architectures, not every step can be probabilistic. When an agent needs to decide whether to approve a loan, which treatment protocol to apply to a patient, or whether to pay an insurance claim, the output needs to be deterministic and explainable.
Alex Porcelli
Co-founder and CEO @Aletyx - Bridging Symbolic AI + GenAI for Enterprise AI, PPMC Apache KIE - 17+ yrs Driving Drools, jBPM and Kogito, Previously @IBM and @Red Hat
Actors for Agents: Patterns for Production AI
Tuesday Jun 2 / 01:20PM EDT
We started with the obvious stack: a prompt-chain framework, some glue code, a queue for the slow parts. It demoed beautifully.
Manju Rajashekhar
Founder & CEO @Mad Labs, Entrepreneur, Engineering Executive, Founder, Investor
The Agent Harness: Control Planes, Invariants, and Approval Boundaries for Production AI Agents
Tuesday Jun 2 / 11:30AM EDT
AI agents can look autonomous, but what keeps them reliable in production is the harness around the model.
Vinoth Govindarajan
Member of Technical Staff @OpenAI, Co-Author of "Engineering Lakehouses with Open Table Formats" and Writes The Agent Stack
Batch Intelligence at Scale: Cost-Efficient Multi-Agent LLM Workflows with Built-In Resilience
Tuesday Jun 2 / 03:40PM EDT
Most teams building production LLM systems face a hard tradeoff: premium models with low latency or cost-efficient inference with unpredictable quality. This talk presents a third path, one validated at Walmart, the largest retailers in the world.
Aditya Mulik
Senior Software Engineer @Walmart Global Tech
Prompt to Prod: Engineering an Autonomous SDLC at Scale
Monday Jun 1 / 03:40PM EDT
Engineering organizations are hitting a Productivity Paradox. AI tools are generating more code than ever, yet the time it takes to ship that code safely to production in large-scale environments remains stagnant.
Andrew Swerdlow
Sr. Director of Software @Roblox, Author of "Tech Leadership: The Blueprint for Evolving from Individual Contributor to Tech Leader", Previously @Google and @Instagram
Your Newest Employee Has Sudo Access: Blueprints to Stop AI Insider Threats
Monday Jun 1 / 10:20AM EDT
Deploying a tool-calling agent is effectively onboarding a new employee who operates at a million actions per minute with database access and zero concept of consequences.
Adrianna Valle
Product Security Engineer @Klaviyo, Author of "Engineering Secure Agentic Systems at Scale", Specializing in the Intersection of Quantitative Data Models and Autonomous System Security
Architecting the Data Layer for AI Agents: From Transactional Systems to MCP and Semantic Models
Monday Jun 1 / 02:30PM EDT
Most conversations about production AI agents focus on the agent itself — the prompts, the orchestration, the framework. But the moment you put an agent in front of real enterprise data, a different problem dominates: the data layer wasn't designed for this consumer.
Fabiane Nardon
Data Expert, Java Champion & Data Platform Director @totvs
Multi-Agent Patterns from Spotify’s AI Powered Advertising Platform
Tuesday Jun 2 / 11:30AM EDT
Spotify's advertising platform spans audience targeting, ad creative generation, campaign goal resolution, budget optimization, and ad campaign recommendations -- workflows that touch different data sources, APIs, and business rules.
Pratik Rasam
Senior Engineer @Spotify
Beyond the Prototype: Scaling Framework Agnostic AI Agent Infrastructure with Ray
Monday Jun 1 / 02:30PM EDT
Building an AI agent is easier than ever. However, moving from a local notebook to a production-grade "Agent Engine" that serves large scale web services poses complex problems.
Deepak Mohanakumar Chandramouli
Senior Machine Learning Engineer @Apple, 20+ Years in Distributed Systems and Scalable Data/Compute/ML Infrastructure
Bhumik Vinodkumar Thakkar
Senior Software Engineer @Apple, Expert in Artificial Intelligence and Large-Scale Distributed Systems
SafeChat: Building AI-Powered Safety Systems at Scale in a Real-Time Marketplace
Monday Jun 1 / 10:20AM EDT
Trust and safety challenges become exponentially harder at marketplace scale, especially when interactions happen in real time.
Bruna Pereira
Software Engineer @DoorDash, 10+ Years in Software Engineering