ShippedHealthcare AIRevenue Cycle
// build study

PriorPilot

An AI prior-authorization and denial-management platform that auto-assembles and submits auths, predicts denials before submission, and drafts the appeals to recover revenue.

Client:Multi-specialty clinic group (NDA)
Duration9 weeks
ScopeMVP product design and front-end build of the Authorization Queue and single-authorization detail experience, backed by a denial-prediction model, a packet-assembly service, and an appeal-drafting engine.

// The Authorization Queue — first-pass approval, turnaround, and denial exposure above a worst-first table of prior-auth requests.

// the numbers

Figures from the engagement, shared under NDA.

We publish them unchanged and can’t break them down any further here. The reference build you can open runs entirely on sample data.

214Auths in flight
88%First-pass approval
1.9 daysAvg turnaround
$146KAt risk in denials
01In brief

If you read one part of this page, read these 4 lines.

  • Predicts likely denials before an auth is ever submitted
  • Auto-assembles payer-ready packets from the order and chart, no manual collation
  • Drafts citation-backed appeals so denied revenue gets recovered on time
  • Every denial-risk score is explainable — weighted gaps, not a black-box number
02Overview

What it does — and which part of it we built.

PriorPilot turns a slow fax-and-phone prior-authorization process into a single triaged queue for a clinic revenue-cycle team.

It reads the order and chart to auto-assemble a payer-ready submission packet, scores each request's denial risk 0–100 before it's sent, tracks status across every payer, and — when a decision goes the wrong way — drafts a citation-backed appeal with re-coding suggestions. BuildspaceLabs designed and built the MVP front end — an Authorization Queue for portfolio triage and a per-authorization detail view for working a denial and its appeal — turning a denial-prediction model and a stream of payer signals into a workflow a biller can act on in minutes.

03The screens

Every screen here is from the reference build, not the client’s system.

The captions say what you are looking at. Every name and record on them is sample data.

04Outcomes

What the engagement left the client with.

  • Delivered a production-quality MVP of the Authorization Queue and authorization detail view in a 9-week engagement
  • Consolidated intake, submission, denial prediction, and appeals into a single revenue-cycle workflow
  • Gave RCM leadership a real-time view of first-pass approval and denial exposure across 214 auths in flight
  • Established a reusable design system (status pills, denial-risk bars, appeal cards) for the product's next surfaces
05How it is built

The stack was picked per constraint, not per house habit.

7 technologies across 3 layers — the shape of the stack follows the problem.

Frontend & Mobile
Next.jsReactTypeScriptTailwind CSS
Data & Infrastructure
PostgreSQL
Backend & APIs
FastAPI · PythonFHIR / HL7 intake
Every feature in the build (6)
  • Authorization Queue with first-pass approval, turnaround, and denial-exposure KPIs over a status-coded requests table
  • 0–100 denial-risk score computed before submission, attributed to specific fixable gaps
  • Auto-assembled submission packets — order, chart notes, imaging, and codes matched to each payer's policy
  • AI-drafted appeals with policy citations, re-coding suggestions, and a peer-to-peer path
  • Live payer tracking across submitted, in-review, info-requested, and decided statuses
  • Denial-reason and per-payer approval and turnaround analytics to fix recurring gaps at the source
// see for yourself

Don’t take our word for it — it is running in the frame below.

This is the same page the provenance block links to: our reference build for PriorPilot, with its own look, copy and motion. Scroll inside it, or open it full-screen.

// more from the lab

A team that ships across the board.

36products in production
8industries served
68+technologies in play

Closest to PriorPilot

// next

Building something in this space?

A 30-minute call is enough for us to understand your situation and tell you whether we're the right team. Usable version in the first two weeks if we are.