Bill Decoder

Turning Medical Bill Confusion Into Refunds, Line By Line

Medical Bill Audit

AI Error Detection

Automated Dispute Letters

Cross-Platform Delivery

HIPAA Compliance

Bill Decoder is a physician-built platform that reads any medical bill, flags the errors line by line, and drafts a dispute letter ready to send. Traditionally, patients face an unreadable wall of codes, long fights with insurers, and no clear way to know what they actually owe.

Bill Decoder set out to change that, turning a phone snapshot of a bill into a confidence-scored audit and a ready-to-sign appeal in under two minutes, before the user even creates an account.

By the Numbers

4 mo

Discovery to launch across web, iOS, and Android

Platforms shipped from one codebase

5★

Clutch review rating

~80%

Of U.S. medical bills contain errors (Healthline)

Four Problems That Had to Be Solved at Once

Diagnostic AI for Messy Real Bills

Medical bills don't arrive as clean PDFs. They run across many pages of densely coded line items the AI has to read in context.

HIPAA Without the Friction Wall

Patients upload bills before creating an account. That means handling PHI from second one, with no authenticated session to lean on.

A Dispute Letter the Patient Could Send

Flagging the error is half the job. The product had to generate a defensible letter citing the right codes and regulations.

Three Platforms, One MVP Timeline

Web, iOS, and Android from a single codebase, on a budget that didn't allow for parallel native teams.

Solution: From Bill to Dispute, in Under 2 Minutes

AI Bill Analysis Engine

Bills run through Hathr.ai on Claude Sonnet 4.5 to catch upcoding, duplicates, and math errors.

Multi-Page Document Processing

Real bills arrive as photos, PDFs, or scans. AWS Textract merges the pages into one readable document.

Auto-Generated Dispute Letters

Once errors are flagged, the app drafts a ready-to-sign letter citing the right codes and regulations.

Confidence Scoring on Every Flag

Each flag gets a High, Medium, or Low rating tied to the evidence, so patients know what to fight first.

Flexible Payment Flow

A no-account upload lets users try before paying. Stripe and RevenueCat handle all checkout.

Admin Console

A back-office panel gives the team a window into user accounts, group management, and bill analyses.

Under the Hood

Why We Bypassed the RAG Layer for the Audit

Challenge

Hathr.ai's standard API wraps Claude in a RAG layer built for general queries. On a bill audit, that layer added noise to the line-item math the result depends on.

Solution

Bypass the RAG layer while keeping Hathr.ai's HIPAA-compliant transport intact.

Extracted text goes straight to Claude, with a preprocessor handling the math.

// bypass RAG, keep HIPAA transport
const text = await textract.extract(bill)
const clean = preprocess(text)   // math + parsing

const audit = await hathr.toClaude({
  model: "sonnet-4.5",
  input: clean,
  rag: false
})

return audit.flags.map(f => ({
  line: f.line,
  confidence: f.score()   // High | Med | Low
}))

A Modern Healthcare Stack Built Around HIPAA-Compliant AI

Priorities

Every tool was chosen to hit two requirements at once: HIPAA-grade handling of patient data, and shipping a testable product across all three platforms on a tight startup timeline.

Technologies

Next.js for the web app.

Capacitor for iOS and Android from one codebase.

Convex for a HIPAA-compliant database.

Hathr.ai as the AI engine.

AWS Textract for document OCR.

Stripe and RevenueCat for payments.

Don't Take Our Word for It

Savings Identified By Users

See how Bill Decoder has helped users understand their bills and flag issues.

★★★★★

"After uploading my hospital bill, Bill Decoder highlighted potential duplicate charges totaling about $1,650. Using the appeal letter, I contacted my insurance company, and the issue was resolved within 30 days."

Sarah from Austin

Identified $1,650 in errors

★★★★★

"Bill Decoder helped me catch something I never would have noticed. Even without an itemized bill, it flagged identical charges from two different specialists and guided me to request more detail before paying. That alone was worth it."

Sammy from California

Identified $367 in errors

★★★★★

"Bill Decoder identified an improper unbundling of colonoscopy procedure codes and helped me generate a clear, evidence-based appeal letter to dispute the $1,599 charge."

Michael from California

Identified $1,599 in errors

Building a Healthcare AI?

We build HIPAA-compliant AI products for healthcare founders, from kickoff to app store inside a single quarter or two.

Book Consultation