Daytona AI Builders - NYC, December 2026
Advertisement
An event dedicated to exploring all things AI Engineering!
Event partners: MongoDB & Nimble
Agenda
🕒 5:30 pm – 6:00 pmWelcome Gathering and Opening Remarks
🎤 Marijan Cipcic, Principal Events Manager at Daytona
🕒 6:00 pm – 6:10 pmTalk "Forkable Sandboxes for Long-Running Agents"
🎤 Muhammad Annas Hashmi, DevRel at Daytona
Outline:
Agents are starting to do real software work: installing dependencies, editing files, running tests, starting servers, and debugging over long sessions. But most AI systems still treat each run like a disposable prompt-response loop. That breaks down once the useful state lives not just in tokens, but in the actual machine.This talk is about the runtime layer agents need to become reliable builders. I’ll show how forkable Daytona sandboxes let you pause at important moments in an agent run, branch the environment, and sample multiple continuations from the same machine state. For builders, this turns long-running agent workflows into something you can inspect, compare, recover, and eventually optimize.
🕒 6:10 pm – 6:20 pmTalk "TBA"
🎤 Speaker from MongoDB
Outline:
TBA
🕒 6:20 pm – 6:30 pmTalk "TBA"
🎤 Speaker from Nimble
Outline:
TBA
🕒 6:30 pm – 6:40 pmTalk "Your System Remembers. Does It Check?"
🎤 Mario Borna Mjertan, Cofounder and CTO at Marktic
Outline:
From metrics and alerts to autonomous investigation
An AI system can store a plausible explanation—and keep trusting it after the evidence changes. Memory alone doesn’t make an agent reliable.
This talk follows a continuous loop: collect, detect, investigate, revisit, and remember. We’ll explore how agents investigate signals without a user prompt, recover context and permissions, evaluate earlier expectations, and revise shared knowledge while preserving the evidence.
A production failure anchors the engineering decisions, tradeoffs, and open questions: when should an agent question what it remembers, how does it check for success, and how does it learn from mistakes.
🕒 6:40 pm – 6:50 pmTalk "TBA"
🎤 Speaker TBA
Outline:
TBA
🕒 6:50 pm - 8:30 pm
Networking
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.
Event partners: MongoDB & Nimble
Agenda
🕒 5:30 pm – 6:00 pmWelcome Gathering and Opening Remarks
🎤 Marijan Cipcic, Principal Events Manager at Daytona
🕒 6:00 pm – 6:10 pmTalk "Forkable Sandboxes for Long-Running Agents"
🎤 Muhammad Annas Hashmi, DevRel at Daytona
Outline:
Agents are starting to do real software work: installing dependencies, editing files, running tests, starting servers, and debugging over long sessions. But most AI systems still treat each run like a disposable prompt-response loop. That breaks down once the useful state lives not just in tokens, but in the actual machine.This talk is about the runtime layer agents need to become reliable builders. I’ll show how forkable Daytona sandboxes let you pause at important moments in an agent run, branch the environment, and sample multiple continuations from the same machine state. For builders, this turns long-running agent workflows into something you can inspect, compare, recover, and eventually optimize.
🕒 6:10 pm – 6:20 pmTalk "TBA"
🎤 Speaker from MongoDB
Outline:
TBA
🕒 6:20 pm – 6:30 pmTalk "TBA"
🎤 Speaker from Nimble
Outline:
TBA
🕒 6:30 pm – 6:40 pmTalk "Your System Remembers. Does It Check?"
🎤 Mario Borna Mjertan, Cofounder and CTO at Marktic
Outline:
From metrics and alerts to autonomous investigation
An AI system can store a plausible explanation—and keep trusting it after the evidence changes. Memory alone doesn’t make an agent reliable.
This talk follows a continuous loop: collect, detect, investigate, revisit, and remember. We’ll explore how agents investigate signals without a user prompt, recover context and permissions, evaluate earlier expectations, and revise shared knowledge while preserving the evidence.
A production failure anchors the engineering decisions, tradeoffs, and open questions: when should an agent question what it remembers, how does it check for success, and how does it learn from mistakes.
🕒 6:40 pm – 6:50 pmTalk "TBA"
🎤 Speaker TBA
Outline:
TBA
🕒 6:50 pm - 8:30 pm
Networking
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.
Advertisement
Where is it happening?
New York, United States
Event Location & Nearby Stays:
Know what’s Happening Next — before everyone else does.
Host or PublisherDaytona



















