Skip to main content
All work

Healthcare

Healthcare Insurance Claims Automation

The hard part: Three government interfaces — OHIP, MCEDT and EDI — each with its own failure modes, running unattended overnight.

OHIP real-time eligibility checks, MCEDT payment reconciliation and automated XML/EDI batch claims. What took a team days now runs overnight without oversight.

  • OHIP + MCEDT
  • Runs overnight, unattended
  • Healthcare platform
  • Canada
  • Shipped 2024
  • Still in production

100%

Claims processed automatically

80%+

Manual data entry eliminated

Overnight

Batch cycle, zero oversight

Healthcare Insurance Claims Automation — Healthcare
Photo: Koen Sweers / Unsplash

How it actually runs

  • Model
  • Guardrail
  • Deterministic
  1. Claim created

    From the platform

  2. OHIP eligibility

    Real-time API verification

  3. Rule validation

    Before every submission

  4. XML/EDI batch

    Generated and submitted overnight

  5. MCEDT reconciliation

    Payments matched automatically

  6. Exception queue

    The few that need a person

The problem

A Canadian healthcare platform was processing OHIP insurance claims by hand. Eligibility checks, payment reconciliation and EDI batch submissions each needed a person in the loop.

The approach

We integrated OHIP APIs for real-time eligibility verification, built MCEDT/WSDL payment reconciliation, and automated XML/EDI batch claim generation with rule-based validation. Exceptions route to a review queue; everything else submits itself.

The outcome

Claims validate, batch and submit overnight. Reconciliation runs on its own. The team reviews exceptions instead of typing claims.

A Canadian healthcare platform was processing OHIP insurance claims by hand. Eligibility checks, payment reconciliation and EDI batch submissions each needed a person in the loop.

The build

  • Real-time OHIP eligibility verification via API
  • MCEDT/WSDL integration for payment reconciliation
  • Automated XML/EDI batch claim generation
  • Rule-based validation before every submission
  • Exception queue for the few claims that need a human

100%

Claims processed automatically

80%+

Manual data entry eliminated

Outcome

Claims are validated, batched and submitted overnight. Reconciliation runs on its own. What took a team days now finishes before the office opens, and the team reviews exceptions instead of typing claims.

Integrated directly into the platform’s ERP, so billing, patient records and payments share one source of truth.

More like this

Conversational AI Agent for Live ERP Data — Enterprise operationsEnterprise operations

NL→SQL

Plain English to live data

100%

Prompt-injection hardened

Conversational AI Agent for Live ERP Data

Every business question needed a developer, and answers arrived days late.

The hard part: Letting non-technical staff query live ERP data without ever giving the model database access.

A natural-language interface over live ERP data. Non-technical staff ask plain-English questions and get ORM-safe, role-gated answers in seconds.

  • Claude MCP over live ERP
  • Enterprise ERP client
  • Shipped 2025

Read case study

Line of Credit Lending Platform — Financial servicesFinancial services

0

Manual steps in the credit lifecycle

100%

Audit trail coverage

Line of Credit Lending Platform

A lending book run out of spreadsheets, where one person understood the formulas.

The hard part: Removing every manual step from a credit lifecycle while keeping a complete audit trail on each state change.

Full lending lifecycle built from scratch: Plaid bank verification, Stripe disbursements and repayments, multi-location credit rules, automated statements and interest.

  • 2 payment rails
  • Lending enterprise
  • Shipped 2024

Read case study

Email Intelligence SaaS Platform — Consumer SaaSConsumer SaaS

5

AI providers unified

3

Scan cadences: 5-min, 2-hr, daily

Email Intelligence SaaS Platform

Turning a Gmail inbox into structured, actionable events — at scale, without leaking a single token.

The hard part: Five AI providers behind one registry, structured outputs schema-checked before anything downstream trusts them.

LLM pipeline that classifies Gmail into structured life events with Zod-validated outputs. Five AI providers behind one gateway, AES-256-GCM token storage, three-tier monetisation.

  • 5 AI providers unified
  • SaaS startup
  • Australia

Read case study

Next step

Discuss a similar build.

Tell us what your version of this problem looks like. The first 45 minutes are free and specific.

Straight to the engineer. No form, no gatekeeper.

Straight to the engineerReply in 4 business hoursNDA on request

Accepting new engagements · Q4 2026