​An event dedicated to exploring all things AI Engineering!

​Agenda

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

​​​​​🎤 Marijan Cipcic, Principal Events Manager at Daytona

​​​​​🎤 Ilias Benabdallah, Relationship Manager & Coby Simler, Product, Growth at Brex

​​​​​​🕒 5:40 pm - 5:55 pm
"Orchestrating Cloud Code: Parallel Sandboxes with Daytona"​

​​🎤 Vedran Jukic, Co-Founder & CTO at Daytona

​​​​Outline:

​​Daytona is an advanced AI sandbox platform delivering lightning-fast, secure infrastructure for running and testing AI-generated code. This demonstration showcases how Daytona Sandboxes transforms Cloud Code into a powerful orchestration platform for distributed development workflows. Using a local Cloud Code instance as the orchestrator, we'll demonstrate how natural language prompts can spawn and manage multiple parallel cloud instances running in isolated sandbox environments—enabling scenarios like parallel test execution across different configurations or coordinated multi-step development tasks.

​🕒 5:55 pm - 6:15 pm
"The future of AI code review and why it's important"

​​🎤 Hunter Brooks, Cofounder & CEO, ellipsis.dev (YC W24)

​​​Outline:

​TBA

​🕒 6:15 pm - 6:30 pm "Velocity Coding"

​​🎤 Ben Guo, Co-founder at Zo Computer

​​​Outline:

​I went viral for spending $9k on Cursor in 1 month, and I wrote half a million lines of code building Zo Computer over the last 4 months. In this talk, I'll share everything I would've wanted to know when I was just getting started. Coding with AI done right is leveraged thinking, and I'll share the workflows we use on our team to ship high-quality code at breakneck speed.​

​​🕒 6:25 pm - 6:35 pm
"Agentic Pentesting & Vulnerability Exploitation"

​🎤 Josh Kotrous, CTO at Pensar

​​​Outline:

​As agentic AI tools grow more capable, they’re also becoming faster at finding and exploiting vulnerabilities. At Pensar we’re building an automated, offensive, continuous pentester that turns that speed into a defensive advantage. In this talk we’ll explain why modern security practices must evolve, demonstrate how an AI can quickly identify and exploit a simple website vulnerability (no step-by-step instructions - demo only), and show how the same agentic approach can run continuously against your codebase to catch and fix issues before they’re weaponized.

​​🕒 6:35 pm - 6:45 pm
"Snap, Sandbox, Summarize: Running Visual LLMs Safely with Daytona"

​​🎤 Lovleen Kaur, Software Engineer III at Cisco

​​​Outline:

​Visual LLMs are powerful, but running them on raw video data can feel risky and heavy. In this talk, I'll showcase a lightweight system that turns short video clips into structured insights in real time using Daytona's agent-native infrastructure. The workflow: capture or upload a quick video, break it into snapshots inside an isolated Daytona sandbox, and send frames to a vision-enabled LLM for analysis. Within seconds, the agent summarizes what’s happening in the video — objects, actions, even context — without ever touching the host environment. Daytona provides the safety net: ephemeral sandboxes that spin up in under 100ms, execute the extraction and model calls, and shut down cleanly. The result is a practical, demo-ready example of how to make visual LLMs both safe and interactive. Whether it’s meetings, product demos, or user-generated content, this approach shows how builders can combine vision models with Daytona’s runtime to unlock new AI-driven experiences without compromising on security or speed.

​🕒 6:45 pm - 6:55 pm
"Production-Ready AI Agents: Lessons from Hundreds of Agent Deployments"

​​🎤 Gabriel Ruttner, 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.

​​​​​​​​​​🕒 6:55 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.