--- title: An Engineering Manager’s crazy year | daily.dev description: An engineering manager at HoneyBook recounts rebuilding his team's workflow three times in a year amid the shift to AI coding tools. The team moved from... canonical: https://daily.dev/posts/an-engineering-manager-s-crazy-year-qdeatqbeh twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: An Engineering Manager’s crazy year | daily.dev og:description: An engineering manager at HoneyBook recounts rebuilding his team's workflow three times in a year amid the shift to AI coding tools. The team moved from... og:url: https://daily.dev/posts/an-engineering-manager-s-crazy-year-qdeatqbeh og:image: https://api.daily.dev/og/posts/QDeATqbEH.png og:image:alt: An Engineering Manager’s crazy year og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # An Engineering Manager’s crazy year **[Manager.dev](https://daily.dev/sources/zaidesanton)** · 24 min read · 11 upvotes · 2 comments ## Summary An engineering manager at HoneyBook recounts rebuilding his team's workflow three times in a year amid the shift to AI coding tools. The team moved from classic Ruby on Rails development with mandatory code reviews to pure vibe coding with Claude Code, dropping code reviews from 2 reviewers to zero. A designer once submitted a 10,000-line PR rewriting the onboarding flow with mocked backend data. The team built an AI assistant called MyCo, initially on an internal ai-workflows system, then migrated roughly 500k lines of code to Vercel's Eve after estimating the old stack made them 50-70% slower; the migration took 7 working days. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What happened when a team stopped doing code reviews after adopting Claude Code for most development? A team at HoneyBook went from having 2 reviewers approve every pull request to having zero reviewers within a couple of months once engineers used Claude Code heavily. The result was a buggy codebase full of duplications and non-optimal patterns, prompting a senior engineer to push for reinstating reviews and the team to add guardrails like a no-comments lint rule and a suppressions ratchet to block new lint debt. _Teams weighing whether AI coding agents still need human review can compare real outcomes like this on daily.dev._ ### Why would a team migrate away from a custom internal AI agent infrastructure like ai-workflows to a product like Vercel Eve? HoneyBook's team switched from its internal ai-workflows system (Python plus Temporal) to Vercel's Eve after estimating the internal system made them 50-70% slower than expected, due to needing coordination across three separately owned repos, confused coding agents reasoning over an oversized codebase, and dependency on another team's deploy schedules and code freezes. Eve was chosen partly because it is built on the open-source ai-sdk library under an Apache 2.0 license, giving an exit route. _Developers deciding between building or buying AI agent infrastructure can weigh real trade-offs like these on daily.dev._ ### How long did it take to migrate a 500,000 line codebase onto a new AI agent framework while continuing feature work? The migration of roughly 500,000 lines of code from three repositories into one, replacing the ai-workflows system with Vercel's Eve, took about 7 working days total for closing the final gaps, after an initial 2-week effort got the migration to 95% complete. The team kept working on the existing codebase in parallel and migrated the delta before a short downtime to cut over user data. _Engineers planning large AI-driven codebase migrations can benchmark timelines against cases like this on daily.dev._ ## Community discussion Top comments from developers on daily.dev. **@kartiknvj** · 4 upvotes > I really like the protect-guardrails hook. An agent can turn a red check green by loosening a lint rule or updating a snapshot instead of fixing the code, and with reviews optional on that backend, nobody would catch it. Blocking edits to lint configs and snapshot images stops it before the PR even exists. **@akkitto** · 2 upvotes > AI is power. Use it wisely. ## Similar posts on daily.dev - [We built dev productivity tools before AI. Here’s what we’ve unlearned since](https://daily.dev/posts/we-built-dev-productivity-tools-before-ai-here-s-what-we-ve-unlearned-since-bcgfjd0ky) · Aviator Blog · 4 upvotes · 0 comments - [The death and revival of the hands-on Engineering Manager](https://daily.dev/posts/the-death-and-revival-of-the-hands-on-engineering-manager-zzd2j1juj) · Manager.dev · 81 upvotes · 11 comments - [Engineering managers have a new job description](https://daily.dev/posts/engineering-managers-have-a-new-job-description-8idlxm623) · LeadDev · 8 upvotes · 1 comments - [The Earth is not flat](https://daily.dev/posts/the-earth-is-not-flat-p5b0sytuz) · Medium · 0 upvotes · 0 comments - [My First Two Weeks as an Agentic Engineer](https://daily.dev/posts/my-first-two-weeks-as-an-agentic-engineer-ibtc3m6h6) · The Miners · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#leadership](https://daily.dev/tags/leadership), [#claude-code](https://daily.dev/tags/claude-code), [#vibe-coding](https://daily.dev/tags/vibe-coding), [#code-review](https://daily.dev/tags/code-review) [View this post on daily.dev](https://daily.dev/posts/an-engineering-manager-s-crazy-year-qdeatqbeh) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"An Engineering Manager’s crazy year","url":"https://daily.dev/posts/an-engineering-manager-s-crazy-year-qdeatqbeh","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/an-engineering-manager-s-crazy-year-qdeatqbeh"},"datePublished":"2026-10-29T19:22:45.774Z","dateModified":"2026-10-29T19:23:17.339Z","description":"An engineering manager at HoneyBook recounts rebuilding his team's workflow three times in a year amid the shift to AI coding tools. The team moved from...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e0aa0739c7857d06efcdf91a31111406?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/e0aa0739c7857d06efcdf91a31111406?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"Manager.dev","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Manager.dev","logo":"https://media.daily.dev/image/upload/s--nwW90hoG--/f_auto/v1731601654/logos/Logo","url":"https://daily.dev/sources/zaidesanton"},"commentCount":2,"discussionUrl":"https://daily.dev/posts/an-engineering-manager-s-crazy-year-qdeatqbeh","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":11},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":2}],"keywords":"ai-agents,leadership,claude-code,vibe-coding,code-review","timeRequired":"PT24M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Manager.dev","item":"https://daily.dev/sources/zaidesanton"},{"@type":"ListItem","position":3,"name":"An Engineering Manager’s crazy year"}]} {"@context":"https://schema.org","@type":"WebPage","@id":"https://daily.dev/posts/an-engineering-manager-s-crazy-year-qdeatqbeh","comment":[{"@type":"Comment","text":"I really like the protect-guardrails hook. An agent can turn a red check green by loosening a lint rule or updating a snapshot instead of fixing the code, and with reviews optional on that backend, nobody would catch it. Blocking edits to lint configs and snapshot images stops it before the PR even exists.","datePublished":"2026-10-30T13:33:38.192Z","url":"https://daily.dev/posts/QDeATqbEH#c-eSPgQ6ooz","author":{"@type":"Person","name":"kartik-nvjk","url":"https://daily.dev/kartiknvj","image":"https://media.daily.dev/image/upload/s--3gGgsVCw--/f_auto/v1781456774/avatars/avatar_TvTVeiMdkRCqWUDullFmy?_a=BAMAMiWQ0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":4}},{"@type":"Comment","text":"AI is power. Use it wisely.","datePublished":"2026-10-29T19:30:44.672Z","url":"https://daily.dev/posts/QDeATqbEH#c-n1FkMXnCo","author":{"@type":"Person","name":"Daniel","url":"https://daily.dev/akkitto","image":"https://media.daily.dev/image/upload/s--FtwJqX4c--/f_auto/v1754900041/avatars/avatar_29TCpY2hJR72V3BlxPXzX?_a=BAMClqZW0"},"interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":2}}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/an-engineering-manager-s-crazy-year-qdeatqbeh#faq","mainEntity":[{"@type":"Question","name":"What happened when a team stopped doing code reviews after adopting Claude Code for most development?","acceptedAnswer":{"@type":"Answer","text":"A team at HoneyBook went from having 2 reviewers approve every pull request to having zero reviewers within a couple of months once engineers used Claude Code heavily. The result was a buggy codebase full of duplications and non-optimal patterns, prompting a senior engineer to push for reinstating reviews and the team to add guardrails like a no-comments lint rule and a suppressions ratchet to block new lint debt. Teams weighing whether AI coding agents still need human review can compare real outcomes like this on daily.dev."}},{"@type":"Question","name":"Why would a team migrate away from a custom internal AI agent infrastructure like ai-workflows to a product like Vercel Eve?","acceptedAnswer":{"@type":"Answer","text":"HoneyBook's team switched from its internal ai-workflows system (Python plus Temporal) to Vercel's Eve after estimating the internal system made them 50-70% slower than expected, due to needing coordination across three separately owned repos, confused coding agents reasoning over an oversized codebase, and dependency on another team's deploy schedules and code freezes. Eve was chosen partly because it is built on the open-source ai-sdk library under an Apache 2.0 license, giving an exit route. Developers deciding between building or buying AI agent infrastructure can weigh real trade-offs like these on daily.dev."}},{"@type":"Question","name":"How long did it take to migrate a 500,000 line codebase onto a new AI agent framework while continuing feature work?","acceptedAnswer":{"@type":"Answer","text":"The migration of roughly 500,000 lines of code from three repositories into one, replacing the ai-workflows system with Vercel's Eve, took about 7 working days total for closing the final gaps, after an initial 2-week effort got the migration to 95% complete. The team kept working on the existing codebase in parallel and migrated the delta before a short downtime to cut over user data. Engineers planning large AI-driven codebase migrations can benchmark timelines against cases like this on daily.dev."}}]} ```