Back to the full page. Use your browser's Print or Save as PDF.

How I Work Like a Thousand-Person Company, With Zero AI Slop

Justin Bartak, Founder and CEO, Orbyt Labs

The short version

AI slop is work that looks finished and is not: it compiles, it reads well, and it is wrong. Justin Bartak keeps it out of his software by testing every change his AI agents make before it ships: a main suite of 39,133 tests on Oct 19, 2026 and, counted October 20, 2026, 46,247 tests across every suite and 100 audit dimensions. When a mistake gets through anyway, it is recorded, and most become a new check. Since July 2026, most new checks have been the agents' own idea.

A team of AI agents, The Machine, runs parts of the company inside the same checks. Everything is connected, so one update spreads everywhere, and the checks are what make that safe.

46,247

tests

100

audit dimensions

712K

lines of code

97

failures on record

Counted

In plain words.

  • Tech debt is the cost of every shortcut you meant to clean up later. It grows quietly until fixing it takes longer than the work itself.
  • AI slop is work that looks finished and is not: it compiles, it reads well, and it is wrong.
  • An audit dimension is a whole category of problem the system checks for on its own, like leaked secrets, broken links or a page AI answer engines cannot quote.

Three real examples.

  • Staff engineer

    Cleanup without a cleanup sprint.

    Six API endpoints, the addresses other programs call for data, each carried about 150 lines of the same setup code, written by hand. One shared piece replaced them. 535 lines came out and behavior stayed identical, down to a known quirk the first lesson below is about, and all 208 tests that check each response’s promised shape stayed green. Five more endpoints moved onto it eleven days later. The house rule is that new read endpoints start from it.

  • Application security engineer

    Security that looks ahead.

    A sweep across 22 classes of vulnerability, plus 15 hands-on probes of the running app, found nothing critical. Every finding worth fixing was fixed the same day. Then the static half of the sweep became a permanent check that runs in CI on every push. Its first run scored 80 percent: one failure was the new check itself being wrong, the other a reviewed exception. After that it scored 100 percent.

  • SEO and answer engine specialist

    Pages built to be quoted.

    The first run across 79 pages found 41 missing the markup that marks a passage as quotable, and 34 answers too long for an engine to lift. Thirteen answers across eight guides were cut to fit, one from 122 words to 76, and on Aug 30, 2026 the strict check returned zero findings. It still reads every page, and it reports any new answer that runs long.

What went wrong, and what it taught the system.

  • The log that lied.

    It taught the system to test that two things agree with each other.

  • The month that ran long.

    Any test that recomputes its own answer the same way the code does is now treated as a red flag.

  • The answers that came back empty.

    A change in someone else's default is now treated as a change to our code.

  • The monitor that only looked at 200 rows.

    A monitor that cannot see is now required to say so, instead of saying everything is fine.

Human in the loop.

I still decide anything that touches money, public claims or the rules themselves. Full autonomy is the goal: right now 145 of 162 recorded agent runs (89.5 percent) made it through the checks to a finished result.

Receipts.