One engineer, 7 months, A$5k: how AI-native development built a production SaaS

What AI-Native Looks Like

Fagner Brack, a solo developer with 20 years of experience, used Claude and Codex to build readplace.com in seven months for under A$5k. The system runs 52 Lambdas, 71 queues, 13,000 tests, and 99.9% uptime, with AI handling code review, CI fixes, and conflict resolution across 50,000 workflow runs. He shares the loop: ground in evidence, implement without committing, review surgically, demand proof, then ship and verify live.

No fancy agent system. No fancy SaaS that promises to simulate employees. Just me, a CLI, and my brain.
  1. randusername

    I'm starting to notice AI power users communicating in a shorthand tech-speak I find unintelligible. I genuinely cannot follow the individual points in this article or what the overall arc is.

    Is this something that was already part of web dev or is it new?

  2. NichoPaolucci

    Does this implementation really require this robust of infra / setup?

    The entire stack feels overkill for a repo that has 2 followers and 29 stars.

    I also am probably not the target demographic though, I just download things that I want to preserve and completely forget about them in a folder called 0_archive.

    I just feel like in 2013 some fella would have had this project running on an old laptop in his garage hooked up to FTP and the uptime would be comparable.

    I also love when AI adds tidbits like this:

    > and staging has to pass before prod deploys.

    Thanks for the clarity on that, Claude, you read my mind.

  3. luc_

    Seems more like AI-in-the-loop more than AI-native.

    I feel like this post didn't teach me anything I didn't already know or have an intuition about.

More from this day

2026-09-23