Inspired by @GiladBarkan's article "From Autocomplete to Intelligence: How Language Became the Operating System of AI", @Wix's Data Science team created a full-day workshop tailored for the design teams they work with. It covered how LLMs work, how context shapes their outputs, and how AI agents plan, remember, and act. Don't miss this insightful article: wix.engineering/post/from-au…

Dashboardless products, zero-downtime migrations, lessons from production incidents, two upcoming meetups and more: Here’s what’s inside our latest @Wix Engineering newsletter - 🚩 Our AI Agent’s Design Looked Complete. 3 Runtime Checks Proved It Wrong / @yoavabrahami Unnecessary APIs, over-engineered types, and an update flow that would leave stale data on screen. Written mostly by the agent itself (!), this account of designing for Wix’s Jay framework shows how human review caught the flaws - with four practical checks for working with AI agents. 🧩 No Dashboard, No Menus: How We Built an Interface Around Intent / Idan Layfer What happens when an AI agent brings users the UI they need? Explore the architecture behind persistent agent-built interfaces, precise data exchange, and synchronized components - and how a merchant launched a cashback program in 10 minutes. 🎮 Stop Reading Your New Codebase. Start Exploring It / Shahar Mayzel You’ve read the files. Are you ready for your first "boss fight"? Approach onboarding like an open-world game: trace end-to-end flows, map dependencies, and use AI as your sidekick to prepare for your first high-stakes change. 🚦 Don’t Offer What Can’t Be Done: Deterministic Executability Gating for LLM Skill Selection at Scale / @AshkenaziOrtal, Vitalii Kloz & Mykhailo Ulianchenko Matching a skill doesn’t mean a user can use it. Across 756K+ production messages, Helpmate’s executability gate filtered out 59.4% of matched skills, reduced skill context by 90.5%, and saved 228.8M tokens. Read the paper on @arXiv. 🛠️ [Upcoming Meetup] Migrations at Scale: Code, Infrastructure & Automation / @Danaavital58 & Shmuel Mekonen From automating changes across hundreds of codebases to migrating 1,000+ MySQL servers across 160+ clusters in 30 days with zero downtime. Explore the architecture, automation, and tradeoffs behind both migrations. Nov 11, 17:30, TLV 🛠️ [Upcoming Meetup 2] Data Agents Beyond the Demo / Yarden Wolf, Eden Bar-Tov. & Jonathan Ohana Bikel Your pipeline is green. Your data is wrong. Can your agent tell? Learn how to automate incident resolution across 8,000+ Airflow DAGs, build domain-aware agents, and catch data issues that pipeline monitoring misses. Nov 23, 17:30, TLV 💪 How to Win in Production: Lessons from Real Incidents at Wix / Guy Nahum Better on-call starts with learning from real failures. Watch Guy unpack production incidents, the patterns they exposed, and practical habits for reducing noise, learning without blame, and using AI responsibly. Read it here: wix.engineering/so/48Q5oFh-L

You've explored dozens of files in your new codebase, but are you ready for your first 🚩 "boss fight" - touching something complex, high-stakes, and unfamiliar? Shahar Mayzel approaches onboarding like an open-world game. Build your map by tracing end-to-end flows, use AI as your sidekick to uncover dependencies and production history, and prepare deliberately before touching critical parts of a system. A practical guide to exploring a new codebase and shipping your first change with confidence: wix.engineering/post/stop-re…

Every hour spent managing website security is an hour taken away from growing a business. At @Wix Engineering, we build security into the platform - from 24/7 threat monitoring to automatic patches and DDoS protection - so you can focus on your growth. Our VP Engineering, @aviranm on why built-in security is a strategic advantage:

An AI skill can match a request perfectly - and still be impossible to execute. @AshkenaziOrtal’s new @arxiv paper explains how @Wix's Helpmate checks account state before skills reach the LLM. Across 756K+ production messages, this filtered out 59.4% of matched candidates and reduced skill context by 90.5%, saving 228.8M tokens. At @Reversim Summit 2026, Ortal will explore this approach as part of her talk on designing, routing, and scaling AI skills in production. Read the papert: arxiv.org/html/2608.01050v1

Building with AI is getting easier. Understanding why it worked - and making it work again - is the harder part. On Nov 2, Amir Harel (Symphony by @Wix) will take the stage at the Claude Community meetup at Wix Campus, TLV, to show how a real feature evolved from a successful experiment into a repeatable process. Good luck, Amir! Details & RSVP: luma.com/claude-9ja6

How do you move critical 🚩 production databases between clusters while millions of users keep using the applications that depend on them? At @Wix, we needed to solve this to improve reliability: when applications share a database cluster, a problem in one can affect the others. Bar Shauli shares how she and our Wix Data Infrastructure team built an internal migration service using Kafka and ProxySQL on top of MySQL, allowing databases to move safely between clusters with zero downtime. From streaming data and handling partitioning challenges to switching live traffic, here's how we make database migrations happen at massive scale-without users noticing. 👉 Read her great blog post: wix.engineering/post/how-we-…

Components help developers manage complexity. But what happens when AI agents have to navigate the boundaries we created? Scattered files, slots, and context can force agents to reconstruct a page before they can safely change it. In this article, @yoavabrahami explores how Jay, a new frontend framework, approaches that challenge through regions: keeping markup local and editable while sharing the underlying logic. You’ll learn how template flattening moves composition from runtime to coding time, how targeted updates keep pages reactive, and how validation and sync preserve local edits as templates evolve. Read here: wix.engineering/post/compone…

What does it take to build agentic products on open-weight models? @ittaiz is speaking at @NVIDIA GTC Berlin 2026! 👏 He'll join a panel exploring why builders are moving to open-weight models, the trade-offs in cost, latency, and quality, and what it takes to run them safely at scale - including what stays on closed models and why. Good luck, Ittai!

What does it take to make on-call better - and turn production incidents into lessons that stick? In "How to Win in Production" Guy Nahum walks through real incidents we've faced at @Wix, the failure patterns they exposed, and the changes that helped us reduce noise and learn without blame. Watch this talk for practical rules and habits you can bring to your team, plus a grounded look at where AI can responsibly help: youtu.be/CaNuUuMsh1k?si=f5wM…