AI Demo Night with Daytona - London, July 2026

An event dedicated to exploring all things AI Engineering!
Event partner: Encode Club
Agenda
🕒 6:00 pm – 6:30 pm
Gathering and networking
🕒 6:30 pm – 6:40 pm
Welcome and Opening Remarks
🎤 Juraj Stefanic, Technical Content Engineer at Daytona

🕒 6:40 pm – 6:55 pm
Talk "Kubernetes Is Not Your Sandbox"
🎤 Mislav Ivanda, DevEx Engineer at Daytona
Outline:
Teams are reaching for Kubernetes to run agent sandboxes, and it's the wrong tool. Kubernetes is built to keep things alive and hold them in a steady state. A sandbox is born, forked, and killed before any of that machinery catches up.

The mismatch compounds because the sandbox keeps gaining requirements without shedding any. In eighteen months it went from a fast code-snippet runner, to a stateful box for long-running agents, to ten thousand ephemeral environments that fork for RL rollouts and die in under a second. It has to be all of those at once, a contradiction set no orchestrator was designed to hold.

The cost shows up the moment you measure it. We ran the same 50-action bug-fix trajectory across five stacks and got a 12x spread: 12.9s on the fastest, 161.5s on the slowest. The gap isn't compute, it's lifecycle overhead per action. We name every stack and explain the mechanism behind each number.

🕒 6:55 pm – 7:10 pm
Talk "Finding Out Where Your Agent Went Wrong, with Phoenix and PXI"
🎤 RL Nabors, Developer Relations Engineer at Arize AI
Outline:
Agents fail quietly, and rarely explain why. This is a live demo showing how to use Phoenix, Arize's open-source evals and observability library, to debug why. Every time an agent runs, it leaves a record, a trace, of what it actually did: which tools it called, what came back, where it broke.

Learn how to point PXI, the agent inside Phoenix, at a pile of traces and find out which ones are worth reading, which are failing, and which ones you can do something about today.

🕒 7:10 pm – 7:25 pm
Talk "Agents, Agents Everywhere"
🎤 Sofía Sánchez-Zárate, Head of Technical Ecosystems at CopilotKit
Outline:
AI agents are only as useful as the surface you can put them in front of. CopilotKit makes that surface any frontend — drop an agent into your existing React app and let it drive real UI, not just chat bubbles. In this talk, I'll show how CopilotKit's generative UI turns agent output into interactive components on the fly, walk through real examples like Slack integrations where agents take action in tools people already use, and demo giving an agent its own isolated Daytona sandbox to safely write and run code, then report back. Expect a fast tour of what "agentic frontend" actually looks like in practice.

🕒 7:25 pm – 7:40 pm
Talk "Think Smaller"
🎤 Tyler Edwards, Co-Founder & CEO of Overmind
Outline:
Using a frontier model on every task is like using a flamethrower to light a candle. Technically works, but your eyebrows and your budget are gone.
Frontier models are overkill for most agent tasks. Specialised small language models, beat them on cost, latency, and accuracy.
Based on this article https://www.overmindlab.ai/research/think-smaller

🕒 7:40 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.