# Wix Engineering

Wix Engineering

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Stop Reading Your New Codebase. Start Exploring It

DevFeed: [Stop Reading Your New Codebase. Start Exploring It](<https://devfeed.tech/articles/stop-reading-your-new-codebase-start-exploring-it-99058.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/stop-reading-your-new-codebase-start-exploring-it>)

Author: Wix Engineering

Published: 2026-10-25T08:15:15Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Learning](<https://devfeed.tech/topics/learning.md>), [Tool](<https://devfeed.tech/topics/tool.md>), [feature flags](<https://devfeed.tech/topics/feature-flags.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [abstraction](<https://devfeed.tech/tags/abstraction.md>), [ads](<https://devfeed.tech/tags/ads.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-tools](<https://devfeed.tech/tags/ai-tools.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [beginner](<https://devfeed.tech/tags/beginner.md>), [cache](<https://devfeed.tech/tags/cache.md>), [clean-code](<https://devfeed.tech/tags/clean-code.md>), [code](<https://devfeed.tech/tags/code.md>), [dependency](<https://devfeed.tech/tags/dependency.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [exploring](<https://devfeed.tech/tags/exploring.md>), [flow](<https://devfeed.tech/tags/flow.md>), [reading](<https://devfeed.tech/tags/reading.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineer](<https://devfeed.tech/tags/software-engineer.md>), [ticket](<https://devfeed.tech/tags/ticket.md>), [tracing](<https://devfeed.tech/tags/tracing.md>)

### AI overview

The author recommends exploring a new codebase around a relevant end-to-end flow instead of reading files in a fixed order or trying to memorize everything. Build a mental map gradually, and look beyond the repository: PRs and commit history explain past decisions, dashboards show runtime behavior, and logs reveal actual user paths. AI tools with MCP integrations can search code and connected sources together, while the engineer remains responsible for understanding and shipping changes. For complex, high-stakes work, first review the feature's context and history, talk to its owners, and identify safe ways to test and roll back changes. The article notes that codebase knowledge is fragmented and that conventions vary between systems.

### Source excerpt

Reading code to onboard onto a new codebase sounds simple until you're actually doing it. You start tracing a single user flow, follow a maze of dependency injections, and before you know it, you've opened more tabs than lines of code you'll actually end up writing, completely disconnected from the ticket on your board. In my five years as a software engineer, most recently on the Paid Ads team at Wix, I've had to do this quite a few times. My default approach was always the same: long code...

## Wix proposes page-local regions to simplify frontend code for AI agents

DevFeed: [Wix proposes page-local regions to simplify frontend code for AI agents](<https://devfeed.tech/articles/components-are-dead-and-now-for-something-completely-different-90000.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/components-are-dead-and-now-for-something-completely-different>)

Author: Wix Engineering

Published: 2026-10-19T11:08:20Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [context-architecture](<https://devfeed.tech/topics/context-architecture.md>), [Fluent Design System](<https://devfeed.tech/topics/fluent-design.md>)

Tags: [all](<https://devfeed.tech/tags/all.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [ast](<https://devfeed.tech/tags/ast.md>), [complex](<https://devfeed.tech/tags/complex.md>), [data](<https://devfeed.tech/tags/data.md>), [design](<https://devfeed.tech/tags/design.md>), [design-system](<https://devfeed.tech/tags/design-system.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [execution](<https://devfeed.tech/tags/execution.md>), [frontend](<https://devfeed.tech/tags/frontend.md>)

### AI overview

Wix Engineering proposes a frontend architecture called Jay that flattens design-system templates into page-local HTML regions while keeping behavior in shared headless components. The post argues this can reduce runtime composition work and make code easier for AI agents to inspect and verify. It describes reactive updates, server-side rendering for static values, and CLI validation and synchronization to detect drift and preserve marked local edits.

### Source excerpt

Introduction The component abstraction was designed to solve a human cognitive limit: a developer cannot hold an entire UI hierarchy in their head, so we learned to encapsulate UI once and reference it across files. But as AI agents increasingly write and maintain frontend code, that trade-off inverted. Agents struggle with multi-file indirection and slot composition seams, but thrive on local context they can see and verify in a single file. Components are the abstraction for humans; regions...

## How Runtime Checks and Design Logs Improved AI-Assisted Feature Design

DevFeed: [How Runtime Checks and Design Logs Improved AI-Assisted Feature Design](<https://devfeed.tech/articles/our-ai-agent-s-design-looked-complete-3-runtime-checks-proved-it-wrong-85226.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/our-ai-agent-s-design-looked-complete-3-runtime-checks-proved-it-wrong>)

Author: Wix Engineering

Published: 2026-10-12T07:09:10Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [AI-enhanced product development](<https://devfeed.tech/topics/ai-enhanced-product-development.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>)

Tags: [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [code](<https://devfeed.tech/tags/code.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [methodology](<https://devfeed.tech/tags/methodology.md>)

### AI overview

Wix Engineering describes how an AI agent helped design a feature for the Jay web framework, then found problems by tracing the design through the actual runtime. The review led to four design log practices: test whether existing primitives are sufficient before adding new mechanisms, follow concrete changes through runtime code, document adjacent mechanisms, and put implementation decisions up front. These checks caught an update bug that abstract reasoning had missed.

### Source excerpt

AI coding agents are remarkably good at producing designs that look complete and convincing. The harder question, especially in complex engineering work, is whether those designs will survive contact with the real world. Working on Jay (our new Jay web framework designed to help AI agents build production-ready websites), we use a strict design log methodology to catch exactly these problems: every significant feature is designed in writing, reviewed, and refined before implementation begins....

## No Dashboard, No Menus: How We Built an Interface Around Intent

DevFeed: [No Dashboard, No Menus: How We Built an Interface Around Intent](<https://devfeed.tech/articles/no-dashboard-no-menus-how-we-built-an-interface-around-intent-64813.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/no-dashboard-no-menus-how-we-built-an-interface-around-intent>)

Author: Wix Engineering

Published: 2026-10-05T07:40:10Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [User interface design](<https://devfeed.tech/topics/ui-design.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>), [Product Management](<https://devfeed.tech/topics/product-management.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [backend](<https://devfeed.tech/tags/backend.md>), [component](<https://devfeed.tech/tags/component.md>), [component-registry](<https://devfeed.tech/tags/component-registry.md>), [product](<https://devfeed.tech/tags/product.md>)

### AI overview

The article explains how Wix built a merchant interface organized around user intent, using an agent to select approved frontend components, show live previews, and guide configuration toward publication. The conversation stores render instructions and confirmed choices, while frontend events synchronize temporary drafts between widgets and previews.

### Source excerpt

Introduction Traditional dashboards force users to hunt through menus and learn complex interfaces before they can complete a simple task. We wanted to reverse that relationship. A merchant should be able to say: "Give customers 10% cashback on orders over $50." From there, the app brings the relevant controls to the merchant, updates a live preview, and guides them toward publishing the configuration. Instead of navigating the product to find the right interface, the merchant describes the...

## From Autocomplete to Intelligence: How Language Became the Operating System of AI

DevFeed: [From Autocomplete to Intelligence: How Language Became the Operating System of AI](<https://devfeed.tech/articles/from-autocomplete-to-intelligence-how-language-became-the-operating-system-of-ai-26632.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/from-autocomplete-to-intelligence-how-language-became-the-operating-system-of-ai>)

Author: Wix Engineering

Published: 2026-09-15T10:17:07Z

Content type: opinion

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Language models](<https://devfeed.tech/topics/language-models.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [article](<https://devfeed.tech/tags/article.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [openai](<https://devfeed.tech/tags/openai.md>)

### AI overview

This article examines why language is closely tied to intelligence in both humans and artificial intelligence. It argues that AI became significantly more powerful by learning language exceptionally well, then introduces how large language models acquire intelligence through models that represent the world and reduce uncertainty.

### Source excerpt

Introduction Every week brings a new AI model, a new coding assistant, a new agent framework. The pace can feel overwhelming. Yet beneath the churn lies a single, surprisingly simple fact - the fact this whole revolution turns on: AI became so powerful because it learned language exceptionally well. In this article I want to step away from the weekly headlines and ask a more basic question: why is language so tightly bound to intelligence - human intelligence in general, and artificial...

## Architecting for 6 Billion Daily Requests: Inside Wix's Media Platform

DevFeed: [Architecting for 6 Billion Daily Requests: Inside Wix's Media Platform](<https://devfeed.tech/articles/architecting-for-6-billion-daily-requests-inside-wix-s-media-platform-22630.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/architecting-for-6-billion-daily-requests-inside-wix-s-media-platform>)

Author: Wix Engineering

Published: 2026-09-08T08:24:05Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Cache](<https://devfeed.tech/topics/cache.md>), [Go Language](<https://devfeed.tech/topics/go-language.md>), [Latency](<https://devfeed.tech/topics/latency.md>), [Compression](<https://devfeed.tech/topics/compression.md>), [data](<https://devfeed.tech/topics/data.md>), [C](<https://devfeed.tech/topics/c.md>)

Tags: [c](<https://devfeed.tech/tags/c.md>), [cache](<https://devfeed.tech/tags/cache.md>), [caching](<https://devfeed.tech/tags/caching.md>), [compression](<https://devfeed.tech/tags/compression.md>), [cpu](<https://devfeed.tech/tags/cpu.md>), [data](<https://devfeed.tech/tags/data.md>), [go](<https://devfeed.tech/tags/go.md>), [latency](<https://devfeed.tech/tags/latency.md>), [technical](<https://devfeed.tech/tags/technical.md>)

### AI overview

Wix describes engineering challenges in its media platform, which processes images, video, and audio at large scale. The supplied text explains how the team used unsafe pointers to reduce Go/C memory-copy overhead for AVIF encoding and a tiered Masters cache to reduce CPU work during image resizing.

### Source excerpt

At Wix, "Media" isn't just about storing files. It's about processing streams of information - images, video, and audio - at an immense scale. We host over 300 million websites and serve more than 6 billion media requests every single day. To handle dozens of petabytes of data while keeping costs low and latency minimal, we had to treat media handling as a complex engineering discipline. Below are five specific technical challenges we faced and the architectural solutions we implemented to...

## 5 Billion Records, 10 Terabytes, Four Weeks: A Real Data Migration Playbook

DevFeed: [5 Billion Records, 10 Terabytes, Four Weeks: A Real Data Migration Playbook](<https://devfeed.tech/articles/5-billion-records-10-terabytes-four-weeks-a-real-data-migration-playbook-22629.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/5-billion-records-10-terabytes-four-weeks-a-real-data-migration-playbook>)

Author: Wix Engineering

Published: 2026-09-02T07:27:50Z

Content type: tutorial

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [data migrations](<https://devfeed.tech/topics/data-migrations.md>), [Database](<https://devfeed.tech/topics/database.md>)

Tags: [data-migration](<https://devfeed.tech/tags/data-migration.md>), [database](<https://devfeed.tech/tags/database.md>)

### AI overview

Wix reports that migration timelines fell from months or years to a few weeks largely because teams identified recurring problems before starting; the tooling changed little. The described approach designs a V2 API, places a proxy before V1, rolls out to new users with a population-based toggle, migrates data with CDC, syncs ongoing changes until V1 is idle, then routes users to V2 and retires V1. A key preparation step is to inspect the source database before writing migration code: legacy data may violate current expectations, such as malformed UUIDs, oversized lists, or implausible birthdates. Since stricter V2 validation can reject records V1 accepted, the excerpt recommends building the migration service's read phase first, connecting it to the source database, and logging suspected inconsistencies. The excerpt cuts off before the rest of that procedure.

### Source excerpt

By the time you finish reading this, someone at Wix is probably in the middle of a data migration. We've run migrations that lasted anywhere from a few months to two years. More recently, we've completed large and complex migrations in a few weeks. The difference wasn't the tooling, which barely changed. It was that we had finally learned which problems show up in every migration, and started dealing with them before the migration began instead of in the middle of it. Recap: Why We Migrate,...

## From Weeks to Hours: Inside Wix's Autonomous Bug-Fixing System

DevFeed: [From Weeks to Hours: Inside Wix's Autonomous Bug-Fixing System](<https://devfeed.tech/articles/from-weeks-to-hours-inside-wix-s-autonomous-bug-fixing-system-22634.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/from-weeks-to-hours-inside-wix-s-autonomous-bug-fixing-system>)

Author: Wix Engineering

Published: 2026-08-19T10:17:19Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Agentic AI](<https://devfeed.tech/topics/what-is-agentic-ai.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [Support](<https://devfeed.tech/topics/support.md>), [observability](<https://devfeed.tech/topics/observability.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [automate](<https://devfeed.tech/tags/automate.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [cancellation](<https://devfeed.tech/tags/cancellation.md>), [code](<https://devfeed.tech/tags/code.md>), [context](<https://devfeed.tech/tags/context.md>), [customer](<https://devfeed.tech/tags/customer.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [issue](<https://devfeed.tech/tags/issue.md>), [jira](<https://devfeed.tech/tags/jira.md>), [queue](<https://devfeed.tech/tags/queue.md>), [services](<https://devfeed.tech/tags/services.md>), [subscription](<https://devfeed.tech/tags/subscription.md>), [support](<https://devfeed.tech/tags/support.md>), [system](<https://devfeed.tech/tags/system.md>), [ticket](<https://devfeed.tech/tags/ticket.md>), [user](<https://devfeed.tech/tags/user.md>), [users](<https://devfeed.tech/tags/users.md>)

### AI overview

Wix Orchestrator aims to cut the time from user bug report to production from weeks or months to under 24 hours by automating context gathering, investigation, fix implementation and code review. Wix identifies missing relevant information--such as the responsible service, logs, prior patterns and whether behavior is intentional--as the main cause of delays, and says the system assembles precise context for agents. A human engineer still reviews and approves every fix before release. The excerpt describes the motivation and core principle, but does not provide the full architecture or evidence of achieved turnaround times.

### Source excerpt

A user opens a support ticket. Their subscription cancellation stopped working. Somewhere inside a system with thousands of services and millions of users, something broke. Before we built Wix Orchestrator, here's what happened next: the ticket joined a queue. Days later, a support engineer picked it up, tried to reproduce the issue, contacted the customer to gather more context, and opened a Jira ticket routed to R&D. We triaged it, prioritized it against everything else on our plate,...

## Code Migrations Don't Have to Hurt. This Is How Switched From Cross Team Manual Work to an Automatic Infrastructure

DevFeed: [Code Migrations Don't Have to Hurt. This Is How Switched From Cross Team Manual Work to an Automatic Infrastructure](<https://devfeed.tech/articles/code-migrations-don-t-have-to-hurt-this-is-how-switched-from-cross-team-manual-work-to-an-automatic-infrastructure-22638.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/how-wix-saved-650-developer-days-in-one-quarter-by-automating-code-migrations>)

Author: Wix Engineering

Published: 2026-07-22T14:10:18Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Pull Request](<https://devfeed.tech/topics/pull-request.md>)

Tags: [change](<https://devfeed.tech/tags/change.md>), [changes](<https://devfeed.tech/tags/changes.md>), [code](<https://devfeed.tech/tags/code.md>), [deprecated](<https://devfeed.tech/tags/deprecated.md>), [google-sheets](<https://devfeed.tech/tags/google-sheets.md>), [infra](<https://devfeed.tech/tags/infra.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [libraries](<https://devfeed.tech/tags/libraries.md>), [managed](<https://devfeed.tech/tags/managed.md>), [migration](<https://devfeed.tech/tags/migration.md>), [migrations](<https://devfeed.tech/tags/migrations.md>), [negotiation](<https://devfeed.tech/tags/negotiation.md>), [priority](<https://devfeed.tech/tags/priority.md>), [projects](<https://devfeed.tech/tags/projects.md>), [slack](<https://devfeed.tech/tags/slack.md>), [team](<https://devfeed.tech/tags/team.md>), [teams](<https://devfeed.tech/tags/teams.md>), [technical](<https://devfeed.tech/tags/technical.md>), [technical-change](<https://devfeed.tech/tags/technical-change.md>), [threads](<https://devfeed.tech/tags/threads.md>)

### AI overview

At Wix, the author reports that 50 migrations affect hundreds of repositories each year, touching 6,000 repositories in total and consuming 25% of developer time. The main bottleneck, they argue, is coordinating engineering attention across teams rather than technical ability. Wix's Code Migration Platform aims to reduce that manual work: migration owners identify affected code, explain a change once, generate pull requests across repositories automatically, and track progress in one place. The excerpt introduces a three-layer architecture but describes only the Migration Dashboard heading, so it does not establish how the other layers work.

### Source excerpt

No one wakes up excited to do a code migration. Deprecated libraries, method version upgrades, infra changes - they happen constantly, they affect dozens of teams, and they always arrive at the worst possible moment. A small technical change somehow becomes months of coordination. Slack threads. Priority negotiation. Manual tracking. Reminders. Many google sheets. For years, I managed cross-team projects at Wix, and migrations were always the hardest part. Not because they're technically...

## The End of Determinism: What's Left for Engineers When AI Writes the Code

DevFeed: [The End of Determinism: What's Left for Engineers When AI Writes the Code](<https://devfeed.tech/articles/the-end-of-determinism-what-s-left-for-engineers-when-ai-writes-the-code-22641.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/the-end-of-determinism-what-s-left-for-engineers-when-ai-writes-the-code>)

Author: Wix Engineering

Published: 2026-07-19T10:33:35Z

Content type: opinion

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Code](<https://devfeed.tech/topics/code.md>), [Programming language](<https://devfeed.tech/topics/programming-language.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [ai](<https://devfeed.tech/tags/ai.md>), [code](<https://devfeed.tech/tags/code.md>), [conference](<https://devfeed.tech/tags/conference.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [fluent](<https://devfeed.tech/tags/fluent.md>), [language](<https://devfeed.tech/tags/language.md>), [programming](<https://devfeed.tech/tags/programming.md>), [programming-language](<https://devfeed.tech/tags/programming-language.md>), [stage](<https://devfeed.tech/tags/stage.md>)

### AI overview

The author argues that engineers' work is shifting from writing code alone to conversing with AI through prompts, iteration, and pushback. They describe shipping AI-written code in a language they do not know fluently and feeling proud of it, using that tension to question what engineering work means as AI takes on more coding. The excerpt frames the change as a shift in cognitive mode, comparing dialogue with the Socratic practice of asking questions to help ideas emerge. It introduces a broader claim that engineering work has changed in three ways, but this excerpt explains only the move from monologue to dialogue.

### Source excerpt

During 2026, I shipped code that I don't fully understand. It was written in a programming language I'm not even fluent in. A year ago, this would have been a fireable offense. There's no way I would have stood on a stage at a Wix Engineering conference, my employers in the crowd, and said that sentence out loud. Last week, it was just another Tuesday. And here's the part that's been keeping me up at night: I was proud of it. That's a paradox, right? If someone else wrote it, I can't be proud...

## A Feedback-Driven Agent Pattern for Self-Repairing AI Workflows

DevFeed: [A Feedback-Driven Agent Pattern for Self-Repairing AI Workflows](<https://devfeed.tech/articles/how-to-build-ai-agents-that-fix-themselves-without-bigger-prompts-more-context-or-another-llm-22635.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/how-to-build-ai-agents-that-fix-themselves-without-bigger-prompts-more-context-or-another-llm>)

Author: Wix Engineering

Published: 2026-07-16T06:17:34Z

Content type: tutorial

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [AI Agent](<https://devfeed.tech/topics/ai-agent.md>), [Code](<https://devfeed.tech/topics/code.md>), [context window](<https://devfeed.tech/topics/context-window.md>), [integrity](<https://devfeed.tech/topics/integrity.md>)

Tags: [agentic-workflows](<https://devfeed.tech/tags/agentic-workflows.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [code](<https://devfeed.tech/tags/code.md>), [context-window](<https://devfeed.tech/tags/context-window.md>), [validation](<https://devfeed.tech/tags/validation.md>)

### AI overview

This tutorial proposes a Feedback-Driven Agent pattern for building self-repairing AI agent workflows. It separates deterministic structural validation from goal-based assessment: agents produce artifacts, programmatic checks identify failures, and structured error reports route the agent toward repair.

### Source excerpt

Every developer building with AI agents eventually hits the same wall. You write a masterpiece of a system prompt, loaded with rules, edge cases, and brand guidelines. It works perfectly... until you add one more rule. Suddenly, the agent gets "context fatigue," ignores half your instructions, and hallucinates a creative but entirely broken solution. We need to stop trying to make agents perfect on the first try. Instead, we suggest a new architectural approach: organizing agentic workflows...

## How We Built the Brain Behind Our Self-Healing System: Context Retrieval at Org Scale

DevFeed: [How We Built the Brain Behind Our Self-Healing System: Context Retrieval at Org Scale](<https://devfeed.tech/articles/how-we-built-the-brain-behind-our-self-healing-system-context-retrieval-at-org-scale-22637.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/how-we-built-the-brain-behind-our-self-healing-system-context-retrieval-at-org-scale>)

Author: Wix Engineering

Published: 2026-07-02T06:58:25Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Model Context Protocol](<https://devfeed.tech/topics/model-context-protocol.md>), [AI-driven information retrieval](<https://devfeed.tech/topics/ai-driven-information-retrieval.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Developer Tools](<https://devfeed.tech/topics/developer-tools.md>), [search-engines](<https://devfeed.tech/topics/search-engines.md>), [Tool](<https://devfeed.tech/topics/tool.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [bug](<https://devfeed.tech/tags/bug.md>), [context](<https://devfeed.tech/tags/context.md>), [engine](<https://devfeed.tech/tags/engine.md>), [explore](<https://devfeed.tech/tags/explore.md>), [github](<https://devfeed.tech/tags/github.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [org](<https://devfeed.tech/tags/org.md>), [repositories](<https://devfeed.tech/tags/repositories.md>), [research](<https://devfeed.tech/tags/research.md>), [scale](<https://devfeed.tech/tags/scale.md>), [search](<https://devfeed.tech/tags/search.md>), [services](<https://devfeed.tech/tags/services.md>), [system](<https://devfeed.tech/tags/system.md>)

### AI overview

At Wix, searching thousands of repositories with simple text matching often returns an irrelevant first hit and misses related services and operational context. To help its autonomous bug-fixing system gather context before attempting fixes, the author built OctoCode, an MCP server on GitHub tooling that helps agents navigate repository relationships and retrieve definitions instead of relying on textual guesses. The excerpt says every tool call requires the agent to state its research goal and reason for calling it. The author reports about 90,000 downloads, 5,000 weekly active users, and 4,500 weekly downloads after eleven months. The supplied text ends mid-description, so it does not establish the full research workflow or further design details.

### Source excerpt

Ask a naive agent to find a bug in a codebase with thousands of repositories, and it will find the first textual match and stop. It won't ask why. It won't check whether what it found is actually relevant. It won't explore related services. It'll just return something and call it done. We, at Wix, discovered this the hard way. And it's what pushed us to build something more deliberate: a research engine that doesn't just search, but reasons about what it's looking for and why. The Problem:...

## From Co-Pilot to Full Automation: How Wix Is Embedding AI Agents Across an Engineering Org at Scale

DevFeed: [From Co-Pilot to Full Automation: How Wix Is Embedding AI Agents Across an Engineering Org at Scale](<https://devfeed.tech/articles/from-co-pilot-to-full-automation-how-wix-is-embedding-ai-agents-across-an-engineering-org-at-scale-22632.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/from-co-pilot-to-full-automation-how-wix-is-embedding-ai-agents-across-an-engineering-org-at-scale>)

Author: Wix Engineering

Published: 2026-05-20T07:28:09Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [Loop Engineering](<https://devfeed.tech/topics/loop-engineering.md>), [codex](<https://devfeed.tech/topics/codex.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-tools](<https://devfeed.tech/tags/ai-coding-tools.md>), [api](<https://devfeed.tech/tags/api.md>), [automation](<https://devfeed.tech/tags/automation.md>), [autonomy](<https://devfeed.tech/tags/autonomy.md>), [browser](<https://devfeed.tech/tags/browser.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cloud-agents](<https://devfeed.tech/tags/cloud-agents.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [coding-tools](<https://devfeed.tech/tags/coding-tools.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [monorepo](<https://devfeed.tech/tags/monorepo.md>), [platform](<https://devfeed.tech/tags/platform.md>), [scale](<https://devfeed.tech/tags/scale.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Wix frames AI coding at its scale--more than 2,500 microservices and thousands of engineers--as an organizational and platform challenge, not simply a matter of adopting tools. The excerpt proposes three tiers: stateless cloud agents with tool access but no persistent files or codebase context; coding agents, or harnesses, that work inside a codebase with an orchestration loop and guardrails; and agents operating a full computer, with broader capabilities and greater risk. It describes harnesses as the practical sweet spot for serious software automation, citing Claude Code, Cursor in agent mode, and GitHub Copilot agent as examples. The excerpt does not provide the promised account of Wix's implementation or results.

### Source excerpt

When you have over 2,500 microservices and thousands of engineers working across a massive multi-product platform, "just use AI coding tools" is not a strategy. It's a starting point - and not a particularly useful one. The question we kept coming back to at Wix wasn't whether to adopt AI in our engineering workflow. That ship had sailed. The question was: what does agentic coding actually look like when you have strong domain boundaries between services, a monorepo with years of...

## How We Built a Zero-Downtime Database Migration Service at Wix

DevFeed: [How We Built a Zero-Downtime Database Migration Service at Wix](<https://devfeed.tech/articles/how-we-built-a-zero-downtime-database-migration-service-at-wix-22636.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/how-we-built-a-zero-downtime-database-migration-service-at-wix>)

Author: Wix Engineering

Published: 2026-05-14T07:19:17Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [data migrations](<https://devfeed.tech/topics/data-migrations.md>), [Database](<https://devfeed.tech/topics/database.md>), [downtime](<https://devfeed.tech/topics/downtime.md>), [self-hosted databases vs managed services](<https://devfeed.tech/topics/self-hosted-databases-vs-managed-services.md>)

Tags: [amazon-msk](<https://devfeed.tech/tags/amazon-msk.md>), [application](<https://devfeed.tech/tags/application.md>), [applications](<https://devfeed.tech/tags/applications.md>), [authentication](<https://devfeed.tech/tags/authentication.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [cluster](<https://devfeed.tech/tags/cluster.md>), [cost](<https://devfeed.tech/tags/cost.md>), [critical](<https://devfeed.tech/tags/critical.md>), [database](<https://devfeed.tech/tags/database.md>), [database-migration](<https://devfeed.tech/tags/database-migration.md>), [db-topology](<https://devfeed.tech/tags/db-topology.md>), [debezium-connector](<https://devfeed.tech/tags/debezium-connector.md>), [domain](<https://devfeed.tech/tags/domain.md>), [downtime](<https://devfeed.tech/tags/downtime.md>), [example](<https://devfeed.tech/tags/example.md>), [good-tools-doesn-t-fit](<https://devfeed.tech/tags/good-tools-doesn-t-fit.md>), [how-db-mover-works](<https://devfeed.tech/tags/how-db-mover-works.md>), [impact](<https://devfeed.tech/tags/impact.md>), [migration](<https://devfeed.tech/tags/migration.md>), [multiple](<https://devfeed.tech/tags/multiple.md>), [operational](<https://devfeed.tech/tags/operational.md>), [optimizing](<https://devfeed.tech/tags/optimizing.md>), [overhead](<https://devfeed.tech/tags/overhead.md>), [service](<https://devfeed.tech/tags/service.md>), [summary-6-key-focal-points](<https://devfeed.tech/tags/summary-6-key-focal-points.md>), [the-challenge](<https://devfeed.tech/tags/the-challenge.md>), [the-python-service](<https://devfeed.tech/tags/the-python-service.md>), [the-result](<https://devfeed.tech/tags/the-result.md>), [zero](<https://devfeed.tech/tags/zero.md>)

### AI overview

Wix built DB Mover to move application databases from shared MySQL clusters to dedicated clusters while aiming for zero downtime, no application code changes, and no data loss. The need arose because problems in one application on a shared cluster could affect critical services such as authentication. Migrations may be reactive, to isolate a service from a troubled cluster, or proactive, for growth, privacy or compliance needs, database upgrades, or cluster organization. Wix's data infrastructure team manages the migrations rather than delegating them to product teams. Its environment uses roughly 200 MySQL clusters, each with two active/passive co-masters across regions, replica nodes, and a ProxySQL layer that routes application traffic. The excerpt introduces other migration tools as unsuitable but does not identify them or explain DB Mover's implementation.

### Source excerpt

The Challenge At Wix, multiple applications share the same DB cluster. The reasons vary: consolidating apps from the same domain, grouping several small apps that don't justify a dedicated cluster, or simply optimizing cost and operational overhead. However, this setup comes with a significant risk: every application on the cluster has the potential to impact all the others. One real example: we had a critical service related to user authentication sharing a DB cluster with several other...

## Wix Migrated Its MySQL EC2 Fleet from Intel CPUs to Graviton

DevFeed: [Wix Migrated Its MySQL EC2 Fleet from Intel CPUs to Graviton](<https://devfeed.tech/articles/1-000-servers-160-clusters-30-days-zero-downtime-migrating-wix-s-mysql-fleet-to-graviton-22627.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/1-000-servers-160-clusters-30-days-zero-downtime-migrating-wix-s-mysql-fleet-to-graviton>)

Author: Wix Engineering

Published: 2026-03-23T11:27:39Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Graviton](<https://devfeed.tech/topics/graviton.md>), [MySQL](<https://devfeed.tech/topics/mysql.md>), [Ansible](<https://devfeed.tech/topics/ansible.md>), [awx](<https://devfeed.tech/topics/awx.md>), [Amazon EC2](<https://devfeed.tech/topics/amazon-ec2.md>), [intel](<https://devfeed.tech/topics/intel.md>), [Database](<https://devfeed.tech/topics/database.md>), [DevOps](<https://devfeed.tech/topics/devops.md>), [Replication](<https://devfeed.tech/topics/replication.md>), [Server](<https://devfeed.tech/topics/server.md>), [Linux](<https://devfeed.tech/topics/linux.md>)

Tags: [amazon](<https://devfeed.tech/tags/amazon.md>), [ansible](<https://devfeed.tech/tags/ansible.md>), [awx](<https://devfeed.tech/tags/awx.md>), [devops](<https://devfeed.tech/tags/devops.md>), [ec2](<https://devfeed.tech/tags/ec2.md>), [graviton](<https://devfeed.tech/tags/graviton.md>), [infra](<https://devfeed.tech/tags/infra.md>), [intel](<https://devfeed.tech/tags/intel.md>), [linux](<https://devfeed.tech/tags/linux.md>), [mysql](<https://devfeed.tech/tags/mysql.md>), [rdbms](<https://devfeed.tech/tags/rdbms.md>), [replication](<https://devfeed.tech/tags/replication.md>)

### AI overview

Wix's DB Infra team migrated more than 1,000 MySQL EC2 servers across over 160 clusters from Intel-based CPUs to Graviton in one month, ahead of the original three-month timeline. The project also enabled a move to Amazon Linux 2023 and away from CentOS 7.0, using AWX workflows and Wix's Dev Portal to automate the process while accounting for replication and cluster reliability concerns.

### Source excerpt

Last January, the DB Infra team at Wix embarked on a strategic and very important mission: Migrating all of our MySQL EC2 servers from Intel based CPUs to the new shiny Graviton ones. Not only will this allow us to work on better CPUs, saving us money and improving our databases, we'll be able to move to Amazon Linux 2023 OS and move from the EOL CentOS 7.0. That sounds simple enough, until you realize that we're dealing with over 1K servers spread over 160+ MySQL clusters. The initial...

## The xEngineer: A New Blueprint for Software Engineering in the AI Era

DevFeed: [The xEngineer: A New Blueprint for Software Engineering in the AI Era](<https://devfeed.tech/articles/the-xengineer-a-new-blueprint-for-software-engineering-in-the-ai-era-22643.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/the-xengineer-a-new-blueprint-for-software-engineering-in-the-ai-era>)

Author: Wix Engineering

Published: 2026-03-16T09:25:50Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [AI Engineering](<https://devfeed.tech/topics/ai-engineering.md>), [engineering-culture](<https://devfeed.tech/topics/engineering-culture.md>)

Tags: [advanced](<https://devfeed.tech/tags/advanced.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [blueprint](<https://devfeed.tech/tags/blueprint.md>), [but](<https://devfeed.tech/tags/but.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [code](<https://devfeed.tech/tags/code.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-assistants](<https://devfeed.tech/tags/coding-assistants.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [decades](<https://devfeed.tech/tags/decades.md>), [engineer](<https://devfeed.tech/tags/engineer.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [era](<https://devfeed.tech/tags/era.md>), [important](<https://devfeed.tech/tags/important.md>), [industry](<https://devfeed.tech/tags/industry.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>)

### AI overview

Wix's "xEngineer" concept shifts engineering value from producing code toward defining problems, designing systems, and orchestrating AI tools. The excerpt says AI use should span the engineering lifecycle, including system design, architectural documentation, debugging, testing, and understanding legacy codebases. For large existing systems, AI can help engineers navigate architecture and make improvements while reducing cognitive load. The excerpt also introduces smaller teams with end-to-end ownership, but cuts off before explaining that principle further.

### Source excerpt

Aviran Mordo, Yaniv Event Haim, Asaf Yonay For decades, the role of the software engineer seemed straightforward: identify a problem and solve it by writing code. But the rise of powerful AI models is beginning to reshape that definition. With systems like Claude Code, Codex, Cursor and other advanced coding assistants, something important has become clear across the industry: writing code itself is gradually becoming a commodity. This does not mean software engineering is becoming less...

## Data-to-Production: Bridging the Gap Between Iceberg and Live Microservices

DevFeed: [Data-to-Production: Bridging the Gap Between Iceberg and Live Microservices](<https://devfeed.tech/articles/data-to-production-bridging-the-gap-between-iceberg-and-live-microservices-22631.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/data-to-production-bridging-the-gap-between-iceberg-and-live-microservices>)

Author: Wix Engineering

Published: 2026-02-17T11:04:08Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [data-engineering](<https://devfeed.tech/topics/data-engineering.md>), [Microservices](<https://devfeed.tech/topics/microservices.md>), [Apache Iceberg](<https://devfeed.tech/topics/apache-iceberg.md>), [Amazon S3](<https://devfeed.tech/topics/amazon-s3.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Apache Spark](<https://devfeed.tech/topics/spark.md>), [etl](<https://devfeed.tech/topics/etl.md>), [Cloud Architecture](<https://devfeed.tech/topics/cloud-architecture.md>)

Tags: [activation](<https://devfeed.tech/tags/activation.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-chat](<https://devfeed.tech/tags/ai-chat.md>), [amazon](<https://devfeed.tech/tags/amazon.md>), [amazon-s3](<https://devfeed.tech/tags/amazon-s3.md>), [analytics](<https://devfeed.tech/tags/analytics.md>), [apache](<https://devfeed.tech/tags/apache.md>), [apache-iceberg](<https://devfeed.tech/tags/apache-iceberg.md>), [availability](<https://devfeed.tech/tags/availability.md>), [backend](<https://devfeed.tech/tags/backend.md>), [challenge](<https://devfeed.tech/tags/challenge.md>), [chat](<https://devfeed.tech/tags/chat.md>), [data](<https://devfeed.tech/tags/data.md>), [data-engineering](<https://devfeed.tech/tags/data-engineering.md>), [data-engineering-teams](<https://devfeed.tech/tags/data-engineering-teams.md>), [data-warehouse](<https://devfeed.tech/tags/data-warehouse.md>), [dwh](<https://devfeed.tech/tags/dwh.md>), [iceberg](<https://devfeed.tech/tags/iceberg.md>), [microservices](<https://devfeed.tech/tags/microservices.md>), [production](<https://devfeed.tech/tags/production.md>)

### AI overview

Wix describes a Data-to-Production platform that moves petabyte-scale data from S3/Iceberg into ClickHouse for low-latency microservice use. It reports ingesting billions of rows for AI Chat Analytics and User Segmentation. The system has a metadata and governance layer, an Airflow/Python ingestion engine, and a Scala type-safe JSON serving API. Product teams register tables through a self-service console using declarative settings for source, urgency, sort keys, partitions, primary keys, and optional TTL. Because sort-key choices can affect ClickHouse cluster health, registration is gated by human review. The excerpt does not include the remainder of that review process or further implementation lessons.

### Source excerpt

At Wix, our Data Warehouse (DWH) is a massive repository of insights. Built on Amazon S3 using Apache Iceberg table formats, and populated by Trino and Spark jobs, it houses petabytes of data--from user segmentation and logs to AI chat analytics. However, storage is only half the battle. The real challenge--and the "holy grail" for many data engineering teams--is Activation : taking that petabyte-scale data and exposing it to backend microservices with millisecond latency, high availability, and...

## From Syntax Checker to Critical Reviewer: How We Convinced AI to Catch Real API Quality Issues

DevFeed: [From Syntax Checker to Critical Reviewer: How We Convinced AI to Catch Real API Quality Issues](<https://devfeed.tech/articles/from-syntax-checker-to-critical-reviewer-how-we-convinced-ai-to-catch-real-api-quality-issues-22633.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/from-syntax-checker-to-critical-reviewer-how-we-forced-ai-to-catch-real-api-quality-issues>)

Author: Wix Engineering

Published: 2026-01-07T10:09:21Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [Developer experience](<https://devfeed.tech/topics/developer-experience.md>), [API](<https://devfeed.tech/topics/api.md>), [Data Quality](<https://devfeed.tech/topics/data-quality.md>)

Tags: [adoption](<https://devfeed.tech/tags/adoption.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-tool](<https://devfeed.tech/tags/ai-tool.md>), [api](<https://devfeed.tech/tags/api.md>), [api-design](<https://devfeed.tech/tags/api-design.md>), [bias](<https://devfeed.tech/tags/bias.md>), [boolean](<https://devfeed.tech/tags/boolean.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [context](<https://devfeed.tech/tags/context.md>), [cooking](<https://devfeed.tech/tags/cooking.md>), [course](<https://devfeed.tech/tags/course.md>), [developer-experience](<https://devfeed.tech/tags/developer-experience.md>), [members](<https://devfeed.tech/tags/members.md>), [mental-models](<https://devfeed.tech/tags/mental-models.md>), [quality](<https://devfeed.tech/tags/quality.md>), [review](<https://devfeed.tech/tags/review.md>), [rules](<https://devfeed.tech/tags/rules.md>), [syntax](<https://devfeed.tech/tags/syntax.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

In API design reviews, the AI caught measurable issues such as vague field descriptions, naming inconsistencies, TODO notes, and formatting errors, but missed usability problems involving workflows, hidden rules, and developers' mental models. The excerpt attributes this gap to the relative ease of checking objective conventions versus reasoning about user context. Its example is an API with APPOINTMENT, CLASS, and COURSE service types that have different rules, including staffing requirements and capacity limits. The article says the team changed its approach to make the model act as a critical reviewer, but this excerpt does not provide those changes.

### Source excerpt

Building an AI tool to review API design taught us something fundamental about how AI approaches quality: it confidently optimizes for the least important parts. Instead of flagging the quality issues that actually hurt developers, like confusing workflows, hidden rules, or inconsistent mental models, it focused on the safe, measurable stuff: naming patterns, formatting mistakes, even typos. Developer experience issues just didn't get caught, even though in our case, we specifically asked for...

## Why I Stop Prompting and Start Logging: The Design-Log Methodology

DevFeed: [Why I Stop Prompting and Start Logging: The Design-Log Methodology](<https://devfeed.tech/articles/why-i-stop-prompting-and-start-logging-the-design-log-methodology-22646.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/why-i-stop-prompting-and-start-logging-the-design-log-methodology>)

Author: Wix Engineering

Published: 2026-01-05T07:29:38Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [AI Context Management](<https://devfeed.tech/topics/ai-context-management.md>), [Spec Driven Development](<https://devfeed.tech/topics/spec-driven-development.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Programming](<https://devfeed.tech/topics/programming.md>), [sdlc](<https://devfeed.tech/topics/sdlc.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [days](<https://devfeed.tech/tags/days.md>), [design](<https://devfeed.tech/tags/design.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [english](<https://devfeed.tech/tags/english.md>), [feature](<https://devfeed.tech/tags/feature.md>), [git](<https://devfeed.tech/tags/git.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [logs](<https://devfeed.tech/tags/logs.md>), [markdown](<https://devfeed.tech/tags/markdown.md>), [methodology](<https://devfeed.tech/tags/methodology.md>), [plan](<https://devfeed.tech/tags/plan.md>), [prompting](<https://devfeed.tech/tags/prompting.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

The Design-Log Methodology uses a version-controlled `./design-log/` folder of timestamped Markdown records so an AI coding assistant can review past decisions before changing code. In the Jay Framework example, a high-level request led the AI to identify related patterns, ask questions recorded in the log, and propose an API and implementation plan for review before coding. Implementation deviations, including serialization choices, were added to the log; the AI suggested separate logs when scope grew. The author reports completing the feature in two days, from initial prompt to a tested pull request. The excerpt presents the method as a way to reduce conflicts with earlier decisions, but ends before the promised explanation of why it works.

### Source excerpt

If you use AI to code, you've felt the "Context Wall." You start a project, things go great, but as the codebase grows, the AI starts making suggestions that conflict with previous decisions. You spend more time correcting the model than writing code To solve this, I developed the Design-Log Methodology. It started as a way for me to remember my own decisions in large projects, but it has become the single most important tool in my AI-coding workflow. The AI is no longer just a "coder"; it is...

## The Wix Engineering 2025 Review: AI, Platforms, Data, and Deep Technical Lessons-Learned

DevFeed: [The Wix Engineering 2025 Review: AI, Platforms, Data, and Deep Technical Lessons-Learned](<https://devfeed.tech/articles/the-wix-engineering-2025-review-ai-platforms-data-and-deep-technical-lessons-learned-22642.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/the-wix-engineering-2025-review-ai-platforms-data-and-deep-technical-lessons-learned>)

Author: Wix Engineering

Published: 2025-12-28T18:29:04Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [Software Engineering](<https://devfeed.tech/topics/software-engineering.md>), [data](<https://devfeed.tech/topics/data.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Retrieval Augmented Generation (RAG)](<https://devfeed.tech/topics/retrieval-augmented-generation-rag.md>), [Software Testing](<https://devfeed.tech/topics/software-testing.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [ai](<https://devfeed.tech/tags/ai.md>), [architecture](<https://devfeed.tech/tags/architecture.md>), [article](<https://devfeed.tech/tags/article.md>), [best-practices](<https://devfeed.tech/tags/best-practices.md>), [blog](<https://devfeed.tech/tags/blog.md>), [data](<https://devfeed.tech/tags/data.md>), [developers](<https://devfeed.tech/tags/developers.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [llm](<https://devfeed.tech/tags/llm.md>), [platforms](<https://devfeed.tech/tags/platforms.md>), [rag](<https://devfeed.tech/tags/rag.md>), [scale](<https://devfeed.tech/tags/scale.md>), [software](<https://devfeed.tech/tags/software.md>), [software-engineering](<https://devfeed.tech/tags/software-engineering.md>), [technical](<https://devfeed.tech/tags/technical.md>)

### AI overview

Wix Engineering's 2025 review curates lessons from building and operating large-scale web systems, covering AI adoption and production systems, platform engineering, data systems, reliability, and software engineering practices.

### Source excerpt

A Year of Building at Scale: Inside Wix Engineering During 2025, Wix Engineering shared deep dives, playbooks, and real-world lessons from building and operating one of the largest web platforms in the world. These stories don't start as content. They start as engineering challenges - some of the most complex, high-scale, and unforgiving challenges modern software teams face. Problems that emerge only when thousands of developers, hundreds of teams, and hundreds of millions of users meet...

## Platform Engineering Extends DevOps by Treating the Internal Developer Platform as a Product

DevFeed: [Platform Engineering Extends DevOps by Treating the Internal Developer Platform as a Product](<https://devfeed.tech/articles/if-you-think-platform-engineering-is-just-devops-you-re-already-behind-22639.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/if-you-think-platform-engineering-is-just-devops-you-re-already-behind>)

Author: Wix Engineering

Published: 2025-12-21T09:12:39Z

Content type: opinion

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Platform Engineering](<https://devfeed.tech/topics/platform-engineering.md>), [DevOps](<https://devfeed.tech/topics/devops.md>), [internal developer platform](<https://devfeed.tech/topics/internal-developer-platform.md>), [Kubernetes](<https://devfeed.tech/topics/kubernetes.md>), [workflow automation](<https://devfeed.tech/topics/workflow-automation.md>), [Deployment Strategies](<https://devfeed.tech/topics/deployment-strategies.md>), [GitHub Actions](<https://devfeed.tech/topics/github-actions.md>), [GitLab](<https://devfeed.tech/topics/gitlab.md>), [Network](<https://devfeed.tech/topics/network.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [automation](<https://devfeed.tech/tags/automation.md>), [deployment-strategies](<https://devfeed.tech/tags/deployment-strategies.md>), [devops](<https://devfeed.tech/tags/devops.md>), [github](<https://devfeed.tech/tags/github.md>), [gitlab](<https://devfeed.tech/tags/gitlab.md>), [internal-developer-platform](<https://devfeed.tech/tags/internal-developer-platform.md>), [kubernetes](<https://devfeed.tech/tags/kubernetes.md>), [networking](<https://devfeed.tech/tags/networking.md>), [pipelines](<https://devfeed.tech/tags/pipelines.md>), [platform-engineering](<https://devfeed.tech/tags/platform-engineering.md>), [policy](<https://devfeed.tech/tags/policy.md>), [workflow-automation](<https://devfeed.tech/tags/workflow-automation.md>)

### AI overview

The article argues that platform engineering is a distinct discipline from DevOps. It focuses on treating an internal developer platform as a product and providing reusable, self-service systems that reduce infrastructure friction and operational complexity for developers.

### Source excerpt

Imagine starting your day as a senior engineering manager at a fast growing tech company. You're barely through your first coffee when your phone lights up with a critical ticket. The Kubernetes environments don't match across stages. DevOps is in place. CI/CD, automation, monitoring, on-call rotations. And still, developers spend more time fighting infrastructure than building products. This is the moment many organizations mistakenly try to "add more DevOps." In reality, this is the moment...

## The Art Behind Better AI: How We Achieved a 46% Speed Boost and 23x Cost Reduction

DevFeed: [The Art Behind Better AI: How We Achieved a 46% Speed Boost and 23x Cost Reduction](<https://devfeed.tech/articles/the-art-behind-better-ai-how-we-achieved-a-46-speed-boost-and-23-cost-reduction-22640.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/the-art-behind-better-ai-how-we-achieved-a-46-speed-boost-and-23-cost-reduction>)

Author: Wix Engineering

Published: 2025-12-09T08:38:23Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [Enhancing AI model performance](<https://devfeed.tech/topics/enhancing-ai-model-performance.md>), [Prompt Engineering](<https://devfeed.tech/topics/prompt-engineering.md>), [llm-reasoning](<https://devfeed.tech/topics/llm-reasoning.md>), [performance-engineering](<https://devfeed.tech/topics/performance-engineering.md>), [software-development](<https://devfeed.tech/topics/software-development.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [ai-agent-development](<https://devfeed.tech/tags/ai-agent-development.md>), [context](<https://devfeed.tech/tags/context.md>), [context-engineering](<https://devfeed.tech/tags/context-engineering.md>), [cost](<https://devfeed.tech/tags/cost.md>), [data](<https://devfeed.tech/tags/data.md>), [fast](<https://devfeed.tech/tags/fast.md>), [faster](<https://devfeed.tech/tags/faster.md>), [flash](<https://devfeed.tech/tags/flash.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-flash](<https://devfeed.tech/tags/gemini-flash.md>), [llm](<https://devfeed.tech/tags/llm.md>), [model](<https://devfeed.tech/tags/model.md>), [performance](<https://devfeed.tech/tags/performance.md>), [performance-metrics](<https://devfeed.tech/tags/performance-metrics.md>), [platform](<https://devfeed.tech/tags/platform.md>), [pro](<https://devfeed.tech/tags/pro.md>), [prompt-engineering](<https://devfeed.tech/tags/prompt-engineering.md>), [speed](<https://devfeed.tech/tags/speed.md>)

### AI overview

Wix reports that preprocessing and ranking scheduling context before sending it to an LLM made contact selection faster and cheaper than relying on prompt tuning with raw data. Its context-engineering layer collects, normalizes, structures, and filters information into a compact list of likely matches, leaving Gemini Flash 2.0 to validate or choose among recommendations. The reported trade-off is more upfront engineering complexity; tests used 150 unique mock-data requests in Wix's internal Evaluation Center. The title reports a 46% speed boost and 23x cost reduction, but the supplied excerpt does not provide the result details or comparison baseline for those figures.

### Source excerpt

Intro: The Limits of Prompt Engineering In modern AI agent development, many teams, including ours at Wix , start with an intense focus on prompt engineering , carefully crafting instructions for the LLM. We iterated endlessly on system messages and instruction sets to solve a core problem: our AI scheduling assistant was struggling with vague requests, such as "Schedule a meeting with Jake." This simple sentence triggers a surprisingly complex challenge. The system must identify which...

## 40% Faster Interaction: How Wix Solved React's Hydration Problem with Selective Hydration and Suspense

DevFeed: [40% Faster Interaction: How Wix Solved React's Hydration Problem with Selective Hydration and Suspense](<https://devfeed.tech/articles/40-faster-interaction-how-wix-solved-react-s-hydration-problem-with-selective-hydration-and-suspense-22628.md>)

Original publisher: [Read original article](<https://www.wix.engineering/post/40-faster-interaction-how-wix-solved-react-s-hydration-problem-with-selective-hydration-and-suspen>)

Author: Wix Engineering

Published: 2025-11-09T12:58:45Z

Content type: article

Language: en

Sources: [Wix Engineering](<https://devfeed.tech/sources/wix-engineering.md>)

Topics: [React](<https://devfeed.tech/topics/react.md>), [performance-optimization](<https://devfeed.tech/topics/performance-optimization.md>), [Interaction to Next Paint](<https://devfeed.tech/topics/interaction-to-next-paint.md>), [Core Web Vitals](<https://devfeed.tech/topics/core-web-vitals.md>), [Page Speed Optimization](<https://devfeed.tech/topics/page-speed-optimization.md>), [mobile optimization](<https://devfeed.tech/topics/mobile-optimization.md>), [Search engine optimization (SEO)](<https://devfeed.tech/topics/seo.md>)

Tags: [2025](<https://devfeed.tech/tags/2025.md>), [browser](<https://devfeed.tech/tags/browser.md>), [cdn](<https://devfeed.tech/tags/cdn.md>), [core-web-vitals](<https://devfeed.tech/tags/core-web-vitals.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [devices](<https://devfeed.tech/tags/devices.md>), [event-listeners](<https://devfeed.tech/tags/event-listeners.md>), [google](<https://devfeed.tech/tags/google.md>), [html](<https://devfeed.tech/tags/html.md>), [industry](<https://devfeed.tech/tags/industry.md>), [inp](<https://devfeed.tech/tags/inp.md>), [interaction-to-next-paint](<https://devfeed.tech/tags/interaction-to-next-paint.md>), [interactive](<https://devfeed.tech/tags/interactive.md>), [javascript](<https://devfeed.tech/tags/javascript.md>), [lcp](<https://devfeed.tech/tags/lcp.md>), [pages](<https://devfeed.tech/tags/pages.md>), [performance](<https://devfeed.tech/tags/performance.md>), [react](<https://devfeed.tech/tags/react.md>), [seo](<https://devfeed.tech/tags/seo.md>), [ssr](<https://devfeed.tech/tags/ssr.md>)

### AI overview

Wix describes a tradeoff in server-side rendering: it improved first paint, SEO, and CDN caching, but every pre-rendered React component still needed client-side JavaScript and hydration before becoming interactive. As sites grew, hydration time and Time-to-Interactive rose, especially on mobile devices; the excerpt reports that fewer than 40% of Wix sites had a "good" INP score. Wix says React 18's Suspense API enabled Selective Hydration, which it used to improve INP while retaining SSR. This excerpt explains the problem and names the approach, but does not provide the implementation steps or evidence behind the title's 40% faster-interaction claim.

### Source excerpt

Introduction For years, one of React's most persistent performance pain points has been hydration. At Wix, where we render hundreds of millions of websites using React and SSR, we've experienced this problem at scale. SSR initially gave us everything we wanted - instant paint, great SEO, and full-site CDN caching. Our pages loaded faster than ever. But as sites grew richer and heavier with content, hydration became a tax we could no longer ignore. The more components a page had, the longer it...