The latest articles on DEV Community by 박성상 (@sungprofile). https://dev.to/sungprofile https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4191820%2Fd0c8309d-b1ae-4ce8-aecd-af0f77df87fa.jpg https://dev.to/sungprofile en 박성상 Sun, 18 Oct 2026 09:23:27 +0000 https://dev.to/sungprofile/i-let-an-ai-coding-agent-build-a-1300-page-ai-claudecode-serverless-webdevsite-with-a-0-server-2hd4 https://dev.to/sungprofile/i-let-an-ai-coding-agent-build-a-1300-page-ai-claudecode-serverless-webdevsite-with-a-0-server-2hd4 <p>I'm not a full-time developer. Over two days and 110 commits I've been running an experiment: I describe what I want in plain Korean, and an AI coding agent (Claude Code) does the planning, coding, deployment, debugging, images and short videos. The result is a Korean information site with 1,360 static pages that rebuilds itself every hour — and the server/API bill is $0 (domain and the AI subscription are separate).</p> <h2> The $0 constraint </h2> <ul> <li>Hosting: GitHub Pages (static HTML) — free</li> <li>Login, bookmarks, visit counter, web-push subscriptions: Cloudflare Workers + D1 free tier</li> <li>Photo-to-ingredients recognition for a "what can I cook with my fridge" tool: a public vision model on Workers AI, capped per day to stay inside the free allocation</li> <li>Data: publishers' public RSS feeds (only where robots.txt allows), Upbit's public crypto API, Google Trends RSS</li> <li>Character art: open models on my own GPU</li> <li>Automation: Windows Task Scheduler on my PC, every hour: collect → process → build → git push</li> </ul> <h2> Things I found interesting </h2> <p><strong>Grouping the same story across 15 news outlets.</strong> The first version linked articles in a chain (A≈B, B≈C), which merged completely different stories A and C. Switching to "compare everything against a seed article" fixed it.</p> <p><strong>A "verification signals" score, not a fact-check verdict.</strong> Each article gets points for cross-reporting, named (vs anonymous or social-media) sources, whether numbers and double-quoted quotes in the headline actually appear in the body, and a flag when outlets report different casualty numbers for the same event. The page always says this is a reading aid, not a final judgement.</p> <p><strong>Analyst reports as nodes.</strong> One brokerage-report article = one node (firm, direction, old → new price target, reason tags). Nodes roll up into per-stock "reasons up / reasons down" trees.</p> <h2> Where the AI got it wrong </h2> <ul> <li>A year-old article without a date slipped into an RSS feed and showed up as "today's report". Fix: resolve dates from RSS → URL → page metadata, drop anything older than 7 days, and flag implausible price-target jumps.</li> <li>Single quotes used for emphasis in Korean headlines were treated as quotations and penalised. Fix: only compare double-quoted text.</li> <li>Generated characters with odd hands. Fix: only hand-checked images are used.</li> </ul> <p>The full cost table, architecture and the actual instructions I gave are on the build log page (in Korean): <a href="https://sungprofile.cloud/ailog/?src=devto" rel="noopener noreferrer">https://sungprofile.cloud/ailog/?src=devto</a></p> <p><strong>Update (Oct 18, evening)</strong></p> <ul> <li>The home page is now four themed entrances; news, money, contests, everyday-life and the AI build log each became a separate screen with its own colours and menu. The entrance matching where you came from (?src=) is shown first.</li> <li>Per-theme chatbots that run entirely in the browser (no model): today's issues and questionable articles; crypto prices and price-target upgrades/downgrades; subsidy search and housing-lottery schedules. Data loads only when the panel is opened.</li> <li>Housing-lottery helper: enter your situation → score (out of 84) + supply types worth trying + matching notices open right now.</li> <li>Money section: an investment-policy table checked against official sources, general age-based principles, and on-the-record expert comments grouped by topic, side by side when they disagree (not investment advice).</li> <li>Search clean-up: RSS feed, sitemap lastmod that only changes when a content hash changes, noindex on thin auto-generated pages, and pre-rendering JS-drawn screens to static HTML (text visible to crawlers went from 687 to 13,605 characters).</li> <li>Analytics: channels grouped by first touch; automated health-check traffic from overseas servers excluded (12 hits had slipped in on day one).</li> <li>Updated numbers: 2 days · 110 commits · 1,360 pages (about 2,400 old multilingual pages removed). Server/API cost is still $0.</li> </ul> ai serverless webdev claudecode