Non-coder had the AI build his personal blog content studio, then tested it until 114 of 114 content blocks matched the original
Korean blogger Jiwon4u, who says he barely codes, had the AI build him a personal 'content studio' (draft generation, private publishing, human review, public publishing, card news, analytics) driven by an 88-line CLAUDE.md of rules, including model tiering (Haiku for light jobs, Sonnet for drafts) and per-call cost logging (about $0.10 per draft conversion). The work queue has run 446 jobs since Sept 30, 2026. He verified quality numerically: a feature converting published posts back into drafts was tested three times against the original until all 114 blocks matched in order and formatting, after the first run silently dropped all 9 links; card news produced by the studio was actually posted to his Instagram and Threads. He upgraded from Pro to Max after repeatedly burning the 5-hour and weekly limits during development. (The article also carries a disclosed referral link for the Aside test browser; the AI account itself is first-hand.)
How it works
- Write structure and rules into CLAUDE.md
- The AI builds the studio (Next.js, queue worker)
- Drafts are generated and privately published
- He reviews before public release
- Conversion quality is tested against originals by block counts (168 sentences, 114 blocks)
- Bugs fixed, worker restarted, same test re-run
- Card news posted to Instagram and Threads
Why it’s worth knowing
The quality bar was numeric, not vibes: he counted blocks and links across three test rounds until the agent-built tool reproduced his posts exactly, 114 of 114.
Where it’s from
Summarized from a public post on jiwon4u.kr. See the original ↗