{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"This Week in NET","title":"We Rebuilt Next.js with AI in One Week (vinext Explained)","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/7673a8f2\"></iframe>","width":"100%","height":180,"duration":1649,"description":"In this episode of This Week in NET (the second this week focused on building with AI), host João Tomé is joined by Steve Faulkner, Engineering Director at Cloudflare, to discuss how he rebuilt a Next.js-compatible framework in just one week using AI. The project, called vinext, began as an experiment and evolved into a working proof of concept.\n\nWe explore what AI-first development looks like in practice, how coding agents were used to rewrite and test large API surfaces, and what happens when you treat dependencies as something you can regenerate rather than maintain manually.\n\nThe results were surprising: faster local builds, smaller bundles, deployment to Workers with a single command, and a total AI token cost of roughly $1,100.\n\nWe also discuss:\n• Using voice-to-code workflows (SuperWhisper + local models)\n• AI reviewing code multiple times\n• Whether AI-assisted rebuilds will become common\n• What this means for 2026 and beyond\n\nMentioned blog posts:\nHow we rebuilt Next.js with AI in one week\n⏱️ Timestamps \n0:12 — Introduction: the latest on the Cloudflare blog (monitoring post-quantum encryption and ASPA routing; JavaScript Streams — why we deserve a better API)\n3:22 — Steve’s role and Workers platform overview\n4:34 — How the idea came to be\n6:11 — When AI tools became “good enough”\n7:13 — Tooling setup: OpenCode, Claude, parallel agents\n9:03 — AI beyond coding: management and markdown workflows\n10:58 — What AI-first development actually means\n12:03 — Performance gains: 4x faster builds, 57% smaller bundles\n14:11 — ~$100 in tokens: the real cost\n15:35 — Deploying to Workers with one command\n17:25 — Community feedback and early adoption\n19:09 — Will AI rebuild other frameworks?\n20:25 — Voice-to-code workflows (SuperWhisper, Parakeet)\n23:31 — Traffic-Aware Pre-Generation (TPR) explained\n25:23 — Production caution and security\n26:19 — How to get started (use AI to migrate your app)\n27:12 — The big takeaway: AI is changing how we build software","thumbnail_url":"https://img.transistorcdn.com/JEk1CAhFcWIBJOFKIzKfdvQ-zUX6aXTuOCJVJJHruOk/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS9jYThl/MjA0YjY3NjRjMzE4/NTdlZTdjMzFjNjll/YTM1YS5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}