Skip to content

Claimify

Claimify is an intelligent pre-submission review workspace that helps healthcare teams produce cleaner claims by validating 837P data against coding rules, payer requirements, and the patient’s clinical record—before den

Code Video Cerebral Valley

Core trick

A deterministic 837P validation engine checks claim fields against coding rules, with a Claude Agent SDK layer that gathers clinical evidence for medical-necessity scores.

Tags

healthfinance

Description

Claimify is an intelligent pre-submission review workspace that helps healthcare teams produce cleaner claims by validating 837P data against coding rules, payer requirements, and the patient’s clinical record—before denials happen.
Akezh/claimify★ 00 forksTypeScriptCreated Jul 19, 2026 · last push Jul 19, 2026

README excerpt

# Claimify

Claimify is a full-stack **Next.js** application for pre-submission healthcare
claim review. Its centerpiece is an **837P professional-claim validation engine
and medical-necessity scorer** with an agentic clinical-evidence layer powered by
the **Claude Agent SDK**. It also includes a lightweight patient documentation
review workflow. Everything — UI, API, data, and AI — runs on a single Next.js
stack with SQLite; no separate backend and no paid API required to demo.

> Demo only. All people, plans, identifiers, notes, claims, and rules are
> fictional or synthetic. This software is not a medical device and does not
> provide clinical or billing advice.

## What's inside

- **837P claims workspace (`/claims`)** — a web form mirroring the 837P structure
  (billing provider 2010AA, subscriber 2010BA, payer 2010BB, claim info 2300,
  diagnosis codes, service lines 2400) prefilled from synthetic FHIR encounters.
  Submit a claim to run three validation layers:
  1. **Structural** (deterministic) — required loops, balanced totals, diagnosis
     pointers, duplicate lines, frequency codes.
  2. **Content & coding** (deterministic) — ICD-10/CPT formats, NPI check digits,
     DOS vs encounter period, place of service, eligibility, provider registry,
     timely filing.
  3. **Clinical evidence** (agentic, Claude Agent SDK) — grounds every billed
     service and diagnosis against the encounter note, transcript, and FHIR
     context, citing verbatim evidence.

  Findings

Team