Scrubs: built for the frontier
What we learned rebuilding intake-to-submission from scratch in thirty days, with most of the code written by AI.
Blog
Product thinking, engineering deep-dives, company announcements, and perspectives from the team building Trusted.
Over the next three years, the winners will not just have better models. They will have better operating systems.
How we put a multi-turn AI agent into production without letting it touch the database. Ninety-two percent of incoming jobs now go live without a human in the loop.
We open-sourced IronTrail, a Postgres-trigger-based change data capture gem. Here's the architectural shift, the metadata pattern that makes it work, and what we learned running it in production for over a year.
What it means to apply on a clinician's behalf, and the four versions plus a manual pilot it took to make that safe. Every guardrail in the current feature exists because something specific broke in production.
A program-shaped surface for the people who run hospital contingent workforce programs, plus the integration-status plumbing that keeps it honest.
What looks like 'call an API' ends up being a multi-quarter engineering investment when UKG is the system of record for who works where.
Forms were the answer when software couldn't understand sentences. Now that it can, we rebuilt clinician validations as conversation and let the model fill the form.
How we rebuilt shift ingestion as a time-blocked demand substrate, and why every higher-order feature in Works depends on it.
Qualification used to take 20 to 30 hours of advocate time per application. Here's the rules engine that does it as structured code, and the AI layer that handles what rules alone can't.