Prior authorization and denial workflows, built read-only in your cloud. Health systems are being pitched ambient scribes, prior auth tools, and denial platforms at the same time. We place a senior engineer with your revenue cycle or patient access team, inside your security process, to test the products against your payer mix and build what they leave out.
Bring your top denial reasons and weekly authorization volume.
Published results in healthcare operations
One prior authorization result and one documentation result, with what each rollout needed.
Atlantic Health System cut its average prior authorization submission time by more than 50% with Waystar automation.
Authorization work was consolidated into one central team, with automation pulling the information each request needs. 60% of authorizations were obtained automatically in the first year.
The Permanente Medical Group's ambient AI scribes saved the equivalent of 1,794 working days of documentation in one year.
7,260 physicians used it over a 63-week evaluation. The top third of users accounted for 89% of use, so adoption work decided most of the result.
Figures as reported by the vendor or customer at the linked source. They are not OpenNash results.
Where our engineer comes in
Atlantic Health centralized its authorization team before automation paid off. At The Permanente Medical Group, a third of physicians drove 89% of scribe use. Both results came from operational work around the product. Our engineer does that work on the laptop your IT issues, through your security review, starting with read-only Epic access.
| Decision | What we look at | Outcome |
|---|---|---|
| Which products to buy | Prior auth, denial, and documentation tools that work with your EHR, tested on your own cases. | Buy where the product covers the workflow. We help with the security review. |
| What to build around them | Your payer mix, EHR build, and the exception cases products miss. | Built for the gaps, read-only first. |
| Where PHI goes | Your cloud account, the model services your security team approved, their processing regions, retention settings, and BAAs. | Documented before any PHI is used. |
| When anything writes back | Epic writeback and payer submission. | Not in the pilot. Added later only with your approval and a review step. |
Why forward-deployed engineers
Built for their largest accounts, deploying their own models. OpenAI's deployment company launched with more than $4B. ↗
Configure their own product, priced per seat or per resolution.
A small senior team, ex-Palantir, Meta, and Databricks. Any model, any vendor. Free pilot, then a flat monthly fee.
Even OpenAI closes the gap with engineers in the room. Source: OpenAI, What FDE means at OpenAI, Oct 2026.
The first eight weeks
Written down with your team in week 1. The pilot is free, and it has to pass these before anything goes further.
Example acceptance tests, not results from a customer deployment. Yours are written with your team.
Systems we work in
Rules from day one
FAQ
The application runs in your cloud account. Before PHI is used, we document which approved model services receive it, where they process it, and the retention settings and BAAs that apply.
Yes, once the scope involves PHI, after a security review with your team.
No. If you want it, we help you choose a product and roll it out, and we build the operational workflows around it.
Why you need one
A senior engineer joins your team on a laptop you issue, tests the options on your data, and puts one healthcare operations workflow into production in 4 to 8 weeks. It starts with a free 14-day pilot judged against test cases you agree in writing.
After launch, we run and improve the workflow on a flat monthly fee, or your team takes it over. The code, tests, and runbook are yours either way.
Bring your top denial reasons and weekly authorization volume.