​An event dedicated to exploring all things AI Engineering!

​Agenda

​​​​​🕒 5:30 pm – 5:40 pm
Welcome and Opening Remarks

​​​​​🎤 Asako Hayase, Pacer - Community Ambassador at Daytona

​​​​​​🕒 5:40 pm - 6:00 pm
Keynote "Run What AI Writes: Secure Sandboxes for Code Generation"

​​🎤 Nikola Radisic, Senior Solutions Engineer at Daytona

​​​Outline:

​Nikola shows how secure, fast, and scalable sandboxes make AI-generated code actually runnable. Learn the technical requirements for building sandboxing tools and how connecting agents to this infrastructure unlocks workflows like analysis, testing, and reinforcement learning.

​🕒 6:00 pm - 6:10 pm
Lightning Talk "Identity Crisis Averted: Auth0 for AI Agents"

​​🎤 Mira Sharma, Product Manager at Auth0 (Okta)

​​​Outline:

​As companies rapidly integrate generative AI into their products and workflows, new identity and security challenges are surfacing—many subtle, high-impact, and not yet widely understood. From prompt injection and agent impersonation to unauthorized API access and data leakage, GenAI systems introduce risks that traditional IAM tools weren’t designed to handle.

​This talk explores the emerging security concerns at the intersection of AI agents, APIs, and identity. We’ll walk through real-world examples of how generative AI can overstep its boundaries—and how to prevent that from happening in production systems.

​We’ll also introduce how Auth0’s approach to securing GenAI helps teams protect users, apps, and agents through standard identity protocols, secure delegation patterns, and policy-driven access control. Whether you’re building internal copilots or external-facing automations, this session will show how to make AI systems secure, auditable, and aligned without reinventing your identity stack.

​​🕒 6:10 pm - 6:20 pm
Lightning Talk "AI Agent Security in Action: Sandboxed Execution with Daytona and Clarifai"

​​🎤 Patrick Lundquist, Staff Engineer at Clarifai

​​​Outline:

​Building and deploying advanced AI agents requires not just powerful models, but also robust and secure infrastructure. This lightning talk will demonstrate how Clarifai's Compute Orchestration platform can be used to manage and execute complex AI models, leveraging Daytona's secure code sandboxes for enhanced security and isolated execution.

​We'll showcase a live demo where a large language model (LLM) is orchestrated on Clarifai's platform, with sensitive or untrusted code execution tasks delegated to a Daytona sandbox. This approach provides a critical layer of security for agentic systems, ensuring that model inferences and their associated logic run in a protected environment. Attendees will see firsthand how to integrate these two powerful platforms to create secure, scalable, and high-performance AI agent deployments. This talk will be highly practical, focusing on the "how-to" for builders looking to implement secure AI workflows.

​​🕒 6:20 pm - 6:30 pm
Lightning Talk "AG-UI: Bringing Agents out of the terminal and into applications"

​​🎤 Uli Barkai, Co-founder at CopilotKit & Tyler Slaton, Senior Founding Engineer at CopilotKit

​​​Outline:

​Most AI agents still live in terminals or the backend—hidden from users. In this talk we will explore user-interactive agents, how to build them, and how AG-UI standardizes the interaction between Agents and frontend applications.

​AG-UI allows developers to build user-interactive agent apps by bringing agents into real applications where they can act, render UI, and collaborate visually with users. It is supported by and built in collaboration with all the top open source frameworks (LangGraph, Crew, Mastra, etc)

​AG-UI also allows for unique context engineering by constantly acting as a bridge serving a continuous flow of application context to agents and agent intent back to the UI.

​​🕒 6:30 pm - 6:40 pm
Lightning Talk "Production-Ready AI Agents: Lessons from Hundreds of Agent Deployments"

​​🎤 Gabe Ruttner, Co-founder & CTO at Hatchet

​​​Outline:

​AI agents in production face a harsh reality: compute crashes, language models drift off task, external APIs fail, and complex workflows break in unexpected ways. After hundreds of agent deployments on Hatchet, we've learned that black-box approaches to agent architecture simply don't scale.

​This talk explores a different path—using framework-agnostic primitives like durable functions and resilient compute to build AI agents that actually work reliably at scale. We'll demo how separating orchestration as asynchronous durable execution from isolated agentic code runtime naturally handles failure recovery while enabling agents to parallelize work effectively without the need for complex state management.

​Whether you're building content generation pipelines, data processing agents, or complex multi-agent workflows, this session will give you concrete strategies for moving beyond proof-of-concept agents to systems that run reliably in production environments where failure isn't an option.

​​🕒 6:40 pm - 6:50 pm
Lightning Talk "Beyond Human Interfaces: Building the Agent-Ready Internet with MCP"

​​🎤 Frederic Barthelet, CTO & Co-founder at Alpic

​​​Outline:

​The internet was built for humans—clicks, taps, visual interfaces. But as AI agents become the dominant users of digital services, this paradigm is breaking down.

​A new agent-native internet is emerging, where LLMs communicate directly with applications through MCP (Model Context Protocol)—no UI required.

​Alpic is the missing infrastructure layer powering this new internet. our all-in-one MCP hosting platform that makes any product "agent-ready" in clicks. Think Vercel for the agent era—while Vercel deployed apps for humans, Alpic deploys apps for agents. Through a live demo, we'll deploy an agent-accessible MCP server with authentication, built-in scaling, and monitoring.

​Whether you're building next-generation AI products or preparing existing services for an agent-driven future, this session shows the infrastructure foundations needed to thrive in the post-UI world where agents are the primary users of your software.

​​🕒 6:50 pm - 7:00 pm
Lightning Talk "Modular auth stack for AI apps"

​​🎤 Satya Devarakonda, Co-Founder & CEO at Scalekit

​​​Outline:

​What we’re building at Scalekit:

​Drop-in OAuth for MCP servers: Our drop-in OAuth2.1 auth layer lets AI and automated agentic clients to securely connect with MCP servers by issuing short-lived scoped tokens, verify JWTs, and expose .well-known metadata for secure communication.

​Agent Connect: A fully-managed auth layer for AI agents to connect to 100+ apps (Slack, Notion, Google, Zoom, etc.) with support for OAuth2, API keys, and user-scoped tokens, along with built-in tool calling and model-optimized connectors.

​​​​​​​​​​🕒 7:00 pm - 8:30 pm

​​Networking

​With pizzas and beverages

​​_________________________________________________________

​​About event

​This is dynamic gathering for AI enthusiasts, innovators, and professionals to collaborate, share ideas, and explore the latest advancements in artificial intelligence. Whether you're building AI products, researching cutting-edge algorithms, or simply passionate about the field, join us to connect, learn, and drive the future of AI forward.