DoorLoop and Node.js-IL meetup
βββ18:00 - Mingling π, SWAG π, pizza π, and beers π»
18:30 - lectures
19:50 - Give a way one Node.TLV 2026 ticket and one PlatforMa 2026 ticket !
β
AI Agentic Development Feedback (Ralph) Loop
βby Neriya (Neri) Rosner, Senior Full-Stack Engineer, DoorLoopβ
βWhat if your AI didnβt just write code, but reviewed, tested, deployed, and fixed it on its own?
βMost AI workflows stop at generation. A developer writes a prompt, reviews the output, finds bugs or architectural issues, rewrites the prompt, and repeats, generating wasted iterations and unused code along the way.
βWe built a different loop: AI that checks itself end-to-end.
βIn this talk, weβll show how our agent starts with fast static feedback using ESLint and TypeScript, validating its code instantly. It runs unit, integration, API, and third-party contract tests, executes real user flows via Playwright MCP, inspects logs during development with Sentry SpotlightJS, commits and pushes to GitHub, and deploys through Vercel, and solves CI issues.
βFinally, weβll show how, using Ralph Loop β built on a Research β Plan β Execute β Review framework β the agent can iterate overnight and continuously develop.
βYouβll leave with a practical blueprint for building fully agentic, self-correcting Node.js workflows.
β
Rules Are Dead. Here's What's Next for AI-First Teams.
βby Or Rozenzweig, Backend Team Lead , Wix.com
βMy AI can read every file in my repo. But it doesn't know why my service exists, what my PM wants, or which patterns my team agreed on over lunch six months ago.
βThat context β the stuff that lives in Slack threads, in people's heads, in tribal knowledge β that's what makes the difference between a nice autocomplete and code that actually ships.
βOver the past few months, my team has been closing that gap. Not with bigger models or better prompts β with structure.
βIn this talk I'll share what's working for me and my team: AGENTS.md for project context, Skills for reusable workflows, and CDD β a way to get your whole team (PM, dev, QA) collaborating through AI agents.
βLive demos, real code, things you can start using Sunday morning.
βDX Guardrails for AI
βby Kiril Reznik, Software Engineer, Aternus | Master Builder
βGet shivers down your spine when you see a PR with 1k+ lines of code changed?
βWith Agentic dev workflows it's easier than ever to get yourself burned out in code reviews.
βSure we could just "ship fast and break stuff", perhaps ask the agent to implement a feature flag, but who's going to operate it when production breaks and an angry customer call wakes you up in the middle of the night?
βJoin me to learn about the guardrails that keep code reviews scalable and DX great.
βTogether we'll explore how SDLC has evolved over the past 2 years and you'll leave with practical tools to keep your sanity and reduce risk of surprises while working with AI.
---------------------------------------------------------
β
Kindly be informed that attendance at the meetup is on a first-come, first-served basis until capacity is reached. Although a place has been reserved for you (after click on attend button), please note that it does not guarantee your spot.