After All Things Open Community Meetup: Agentic AI in the Wild: Open Source Agents in Production
Date & Time
THU 22 OCT
Capacity
Open
About
AI and Open Source Builders Meetup, New York City AI agents are moving into production, and more and more of them are built on open source. The question is no longer whether to use them, but how to make them reliable after the demo. This meetup brings together builders, maintainers, and practitioners integrating AI agents into real codebases, CI/CD pipelines, internal developer platforms, cloud native infrastructure, and observability stacks. The evening focuses on the conversations that rarely fit into conference talks: what breaks at scale, how open source tools and standards shape agentic systems, where failure modes hide, and 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 and security, and 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 and Networking 5:30 PM Welcome and Opening Remarks 5:40 PM Dana Fine, Qodo Dev Community 6:05 PM Break, Food and Networking 6:25 PM Panel: Agentic AI in the Wild: Open Source Agents in Production 7:15 PM Ryan Hamilton, Senior Developer and Community Lead, CircleCI AI Lab 7:40 PM Closing Remarks 7:45 PM Networking until 8:00 PM Speakers and Sessions Dana Fine, Qodo, Developer Relations & Open Source Lead
Bio: Dana Fine is the Developer Relations & Open Source Lead at Qodo, where she established the Qodo Dev Community, and a maintainer of the open source project PR-Agent. She leads GitHub User Group Israel, CNCF Israel and AAIF Tel Aviv, and is a former GitHub Star and CNCF Ambassador. She is passionate about bringing people and communities together, keeping open source open, and getting more women on stage. Talk title: Too Many PRs at my OSS Community
Abstract: Open source runs the economy, and AI just flooded it with pull requests. Writing a PR is now almost free, but reviewing one still costs a maintainer’s evening. Ghostty, tldraw and curl are already closing the gate. This talk shows a better way: don’t close the gate, scale the gatekeeper. Learn how to turn your guidelines into rules that agents enforce on every PR, so slop gets rejected, the queue gets ranked, and every review makes the next one smarter. You’ll leave with steps to try on your repo the same night. Ryan Hamilton, Senior Developer and Community Lead, CircleCI AI Lab
Talk title: Engineering Agent Loops That Ship 100% Green PRs on the First Push
Abstract: 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, and 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, and 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, and what role does open source play? Practitioners from across the stack will discuss context management, governance, open standards, observability, security, and what changes when agentic systems scale. Expect concrete lessons, not talking points. Moderator: Jai Bhagat, DevRel, PrismML Panelists:
- Miriam Lebowitz, Developer Relations Manager, AI Natives, NVIDIA Miriam is a Developer Relations Manager (DevRel) on NVIDIA's AI Natives team, where she helps AI-first companies build and scale with NVIDIA technology and makes sure their feedback shapes what NVIDIA builds next.
- Baruch Sadogursky, Port - Baruch is a longtime developer advocate and a well-known speaker at developer conferences around the world. He co-authored Liquid Software and DevOps Tools for Java Developers, and focuses on developer productivity, DevOps, and how AI is changing the way software gets built and shipped.
- Jay Messina, Senior Software Engineer, Qodo Jay Messina is a Senior Software Engineer at Qodo, where he focuses on building reliable, scalable data systems. He began his career developing AI applications at IBM before moving into technical leadership roles at New York City startups. With experience spanning real-time analytics, financial infrastructure, and distributed systems, Jay is passionate about mentoring engineers, solving complex technical challenges, and helping teams turn innovative ideas into production-ready solutions. Community Partners All Things Open, Qodo Dev Community, Frontend NYC, WeMakeDevs, Bond AI