I’m John Kueh, an applied AI engineer in Sydney. I build agents that do real work in production: they research, write, test and ship.
One watches viral TikToks and Reels like a content strategist and tells creators which hooks to steal, with the videos as proof. Another grew a medical wiki to 1.4m search impressions while checking every claim against its sources. At Clove, where two of us took the app to 100k monthly users, agents triage support tickets and draft fixes from bug reports.
Flare is my own backend for apps, on Cloudflare: offline-first sync, auth, feature flags, analytics and crash reports from one Rust core. GLP3, Snuglog and LedgerSignal already report through it.
reels.chat is an agent that watches viral TikToks and Reels and hands back the hooks that worked, with the videos as receipts. Its model mix is chosen by evals; one run screened 2,752 videos and watched 150.
GLP3 is a medical wiki run by an autonomous SEO loop that checks its sources before it writes, plus a tracking app. It grew from zero to 1.4m search impressions.
Snuglog is a calm baby tracker for 3am: one tap per feed, nap or diaper, and a care plan for eczema and allergies.
LedgerSignal reads thousands of bank transactions for insolvency teams and flags the payments worth recovering.
I write about what happens when agents do the work:
- July 2026A Wendy for a team of one
- June 2026I let Claude run a peptide wiki I knew nothing about
- June 2026I mined 224 transcripts to salvage a model too good to be legal
- June 2026My skills go stale in two months
- June 2026A cinematic hero for 80 cents
The agents run on skills I share in the open. Install the lot in Claude Code, Codex or Grok, or take one:
Synced from github.com/johnkueh/agent-skills on every deploy.
Building something with agents and want a second pair of hands?
Email me ›