552.studio
A studio building software with an AI production line. New York.
We make software with AI doing most of the building. This site shows the five products that came out of it, what broke along the way, and what we learned.
deterministic controls around nondeterministic intelligence
552.studio runs an AI production line that plans, builds, verifies its own work and records what broke. Since January 2026, five products came out of it. This page is the record of what the studio builds and how the line works.
By the numbers
the line, by the numbers
Every job starts as a written ask. Scheduled AI workers build and test it. The numbers below are what that has produced.
Projects
all work →five products · the 552.studio portfolio — each row opens its page
How they get made
seven stations · this page is built and tested on the same line
Work goes in as a written ask and comes out as a merged pull request. Between the two, the line plans it, builds it, and proves it works before anyone sees it. Every change must pass its tests and an automated review; changes to deployment, to what the loop may do, or to its written rules wait for the operator to read them before they merge, and everything else merges once its checks pass and is read afterwards, with a revert path. What broke gets written down and feeds the next pass.
the full walk-through →Writing
what the line learned; a spark is a numbered lesson written after a failure
About
the short version
552.studio is a studio in New York building software with an AI production line: a written ask goes in, and a tested, reviewed pull request comes out. The studio is run by its founder, whose background is a decade of payments and technology programs and controls — the discipline behind the line's gates: every change is verified before it merges, and what breaks is written down.
Perse is the engine that runs the line: the half of an AI system that lives around the model, run like a program. Work enters as a Form with acceptance criteria naming a checkable artifact; scheduled AI workers shape, build, check and document it, and a worker plans against the repository and calls real tools. Failure is designed for: typed returns, parked premises, reaped sessions, and a liveness check that trusts evidence of a run over a worker's own report. Memory lives in Postgres, not the context window.
Founder
Julio David Ochoa, founder of 552.studio.
In regulated work the bar is not whether AI is impressive but whether its output can be reviewed, reproduced, and defended. A solo hackathon build, finished in 24 hours, turns business ideas into reusable AI artifacts and stops loudly when live inference fails. A curated-knowledge assistant discloses its confidence with every answer and says it does not know rather than guess. Every AI-assisted workflow carries subject-matter review before formal use.
What holds my attention: AI platforms and tooling that can be inspected and audited rather than merely trusted; governance built into the system instead of written next to it; and how a small team, or one person with a production line, ships work that holds up under partners, regulators, auditors, and production.
Contact
Write to the studio
What the studio works on: AI platforms and tooling that can be inspected and audited rather than merely trusted, and governance built into the system instead of written next to it.
emailjulio@552.studio