| |
|
| |
AI & Open Source Builders Meetup, New York City
AI agents are moving into production, & more & more of them are built on open source. The question is no longer whether to use them, but what it takes to make them reliable once the demo is over.
This meetup brings together builders, maintainers, & practitioners integrating AI agents into real codebases, CI/CD pipelines, internal developer platforms, cloud native infrastructure, & observability stacks.
The evening focuses on the conversations that rarely fit into conference talks: what breaks at scale, how open source tools & standards shape agentic systems, where failure modes hide, & how teams build systems they can trust.
Under the theme Open Source in Production, we will explore agentic code review, agent loops in CI/CD, developer platforms, eBPF-powered observability & security, & the role open source communities play in how production AI gets built.
No vendor pitches. Just practical lessons from systems running in production.
Agenda
5:00 PM Doors Open, Drinks & Networking
5:30 PM Welcome & Opening Remarks
5:40 PM [Speaker TBD], Qodo Dev Community
6:05 PM Break, Food & Networking
6:25 PM Panel: Agentic AI in the Wild
7:15 PM Ryan Hamilton, Senior Developer & Community Lead, CircleCI AI Lab
7:40 PM Closing Remarks
7:45 PM Networking until 8:00 PM
Speakers & Sessions
[Speaker TBD], Qodo
[Talk title TBD]
[Talk abstract TBD]
Ryan Hamilton, Senior Developer & Community Lead, CircleCI AI Lab
One Take: Engineering Agent Loops That Ship 100% Green PRs on the First Push
Most teams optimizing AI-assisted development are focused on the wrong variable: prompting harder, adding rework, dumping larger failure logs into context. The real question isn't how to fix red PRs faster. It's how to stop producing them.
Ryan shares findings from three connected Loop Lab experiments, each using the same controlled Snake game benchmark to isolate one variable at a time. Each one reveals something unexpected about where the real leverage lives in an agent loop, & what it means for cutting the cost of agentic development.
Together, these experiments map a clear path from "rework is inevitable" to "rework is reserved for the unknowable." The result is a practical harness design that bakes a low Merge Efficiency Ratio (MER, the number of validation cycles it takes to get a change onto main) in from the start, & a new way to think about where validation belongs in the agent loop.
Panel: Agentic AI in the Wild
What does it take to move AI agents from proof of concept into systems that operate reliably, & what role does open source play?
Practitioners from across the stack will discuss context management, governance, open standards, observability, security, & what changes when agentic systems scale.
Expect concrete lessons, not talking points.
Moderator
Dana Fine, Open Source & Developer Relations Manager, Qodo
Dana leads open source programs & community initiatives at Qodo. She runs the GitHub User Group, CNCF local & GenAI communities, & the Bond AI meetup series.
Panelists
Baruch Sadogursky, Port
Baruch is a longtime developer advocate & a well-known speaker at developer conferences around the world. He co-authored Liquid Software & DevOps Tools for Java Developers, & focuses on developer productivity, DevOps, & how AI is changing the way software gets built & shipped.
[Speaker TBD], Claude Community
[Bio TBD]
[Speaker TBD], NVIDIA
[Bio TBD]
Community Partners
AWS User Group NYC, CNCF NYC, Frontend NYC, WeMakeDevs, Bond AI, Qodo Dev Community
Join the Community
Qodo Dev Community on Discord: [Discord invite link]
Follow us on Meetup: [Meetup group link]
|
|
|
|
|
|
|
|
