AI TALKS in the City: From Vibe to Flow

We are excited to expand our event series to NYC during AWS Summit NYC Week with: On the Agenda: 5:30PM 🍻🍕🤓 Mingling and Nosh Moderated by: Sharone Revah Zitzman, Chief DevRel, RTFM Please 6:00PM 🎙️Short Talks LLM-Powered Dev Workflows, Thomas Wood, Senior Director of Field Engineering and Customer Success, Root.io From Helpers to Doers: Achieving 5X Velocity Imperfect Is Fine (When It’s You), Lev Andelman, CTO, TeraSky Humans hallucinate memories, forget decisions, and confidently state wrong facts - and we built entire civilizations around it. Yet when AI does the same, we call it broken. This talk uses cognitive science, live audience experiments, and real-world engineering failures to expose the double standard killing your AI adoption. You’ll leave with a practical framework: validate the output, not the process - and stop demanding perfection from AI that you never demanded from yourself. ⚡️ LIGHTNING TALKS ⚡️ HOT TAKE: We Don’t Need Code Reviews - How AI is Changing the Last Sacred Engineering Ritual, Noam Levy, Field CTO, groundcover Code review is treated as the final safety net of modern software engineering. That assumption is quietly breaking down as AI writes most of our code. In many teams today, LLMs generate refactors, tests, fixes, and migrations. The author reviews the code, runs tests, validates behavior, and understands the change end to end. Then they are still required to perform the sacred ritual of opening a pull request and waiting for approval. Days later, an async human review arrives from someone with less context and worse tooling. The result looks like rigor, but mostly adds delay and shallow feedback. This talk argues that traditional PR review has become theater in an AI-driven workflow. AI tools already catch style issues, missing error handling, security risks, and best-practice violations faster and more consistently than humans. Meanwhile, the failures that actually matter, performance, edge cases, operational impact, are rarely caught by late, asynchronous reviews anyway. Based on real production workflows, the session proposes a shift to AI-assisted self-review - engineers own their changes end-to-end, AI enforces consistency and standards, and human review moves to where it adds real value - design discussions, architecture decisions, and mentorship. If AI has fundamentally changed how we write code, it’s time to change how we decide it’s safe to ship. Beyond Cargo Culting: Reproducibility Reconsidered, Stephen Swoyer, Technical Staff, Flox Because software delivery has standardized on containers and VMs, we've come to see strict isolation as necessary for reproducibility. But this is cargo-culting: mistaking a pattern for a first principle. Agentic AI lets us see this clearly: We jail agents in sandbox hoosegows because we can't trust what they'll do on their own. Why, then, do we insist on isolating human developers in dev containers and other jails? Disentangling isolation from reproducibility means developers no longer pay for one just to get the other. 7:35PM More mingling, networking and AI nerdery