Founder & Lead Engineer Feb 2026 – Present

InsurifyAI

AI Insurance Claims Platform

When an insurer undervalues a claim, InsurifyAI builds the evidence and sends the demand: letters that cite state bad-faith statutes and NADA + KBB + Manheim comparables, USPS Certified Mail via Lob with tracking saved to the claim, and real-time AI coaching during adjuster calls. Founded on a real Tesla settlement that grew from $17,262 to $29,155 — a +68.9% recovery — through 211 pages of legal evidence. Under the hood: 33 production dashboard pages and a 21-agent Shadow Team that ships the roadmap.

Next.js AWS Fargate Terraform Supabase Claude API Stripe Lob
Impact

By the Numbers

+$11.9K
Founding Recovery
$17,262 → $29,155 negotiated on Tesla settlement (+68.9%)
2
Live Deployments
Tesla settlement + homeowner's claim
211
Page Demand Packet
Numbered exhibits, citations, and Bates stamps
5
ECS Services
API · Web · Realtime · Agent-Hub · Agent-Runtime
123
Terraform Resources
VPC, RDS, Redis, CloudFront, WAF, ECS
21
Autonomous Agents
Shadow Team agents shipping PRs across tiers
33
Dashboard Pages
Liquid Glass design system, all production
28
Email Addresses
Cloudflare Email Routing + SendGrid relay
Capabilities

Core Features

InsurifyAI fuses insurance domain expertise with full-stack engineering and a fleet of autonomous AI agents. Each capability was built to win specific carrier-disputed claims — not as a hypothetical feature list.

Real-Time Voice Coaching

Live transcript + AI-suggested rebuttals during recorded claims calls. Coach insureds through adjuster calls in real time using Claude + WebRTC streaming.

Demand Letter Generation

python-docx pipeline produces formal document layouts with exhibit numbering, citation formatting, and Bates stamps. Each letter cross-references NADA + KBB + Manheim valuations and applicable state statutes.

Shadow Team Autonomous Agents

21 AI coding agents work the feature roadmap by opening pull requests. Every PR goes through automated tests and merge gates, and escalates to human review by risk tier. Each agent runs within budget guardrails.

Certified Mail Delivery

Lob API integration handles USPS Certified Mail dispatch. Letters print, envelope, and ship with tracking numbers captured automatically as proof of delivery for the claim record.

Liquid Glass Design System

Apple HIG-inspired UI with translucent panels and depth-aware components shipped across all 33 dashboard pages. Built on shadcn/ui with custom material overlays.

State-Specific Legal Database

50-state legal database with bad-faith statutes, statute of limitations, and CCC ONE valuation methodology. Letters cite the specific applicable statute per claim location.

On Film

Watch it work

Three cuts of the same product: the spot that explains the problem, the walkthrough that proves the platform does the work, and the version aimed at the body shops that refer into it.

Product walkthrough — 2:56. The founding claim end to end: the carrier's own CCC ONE valuation at $17,262, the comparable-vehicle workup, the 211-page demand package, and the $29,155 settlement. Every figure on screen comes from the carrier's documents.
The ad — 34s. Built in Palmier Pro from generated footage, with the product beats captured from the live site. One flat fee, never a cut of the settlement.
For body shops — 1:27. The partner-side story: free listing, referral share, wholesale tiers, and why it is not only for totaled cars.
Founding Case Study

Tesla Settlement Demand — $17,262 → $29,155

The real-world legal claim that drove the platform: a 2019 Tesla Model 3 case involving FSD, CCC ONE valuation disputes, and a December 2025 incident. State Farm's adjusted vehicle value was $17,262. Through a 211-page legal demand packet delivered via USPS Certified Mail, the State Farm Claims Upload Center, and email, the settlement was negotiated to $29,155 — a +68.9% increase, $11,893 more than the initial offer. Every workflow now automated by InsurifyAI started here.

Why this approach worked: insurance domain expertise (50-state legal database, CCC ONE valuation methodology, NH bad-faith statutes), technical precision (python-docx formatter for formal layouts), cross-referenced evidence (NADA + KBB + Manheim comparables, FSD-specific damage docs, policy language analysis), and the full stack — engineering to build the tools, business to negotiate the leverage, insurance domain to identify the carrier's weak points.

Architecture

Technical Architecture

InsurifyAI runs on AWS Fargate with 5 ECS services, 123 Terraform-managed resources, a Supabase Auth + Postgres backend (pgvector for legal-document search), and a Next.js App Router frontend. Shadow Team agents operate against the same data plane with tiered PR routing.

Backend

  • 5 ECS Fargate services (API, Web, Realtime, Agent-Hub, Agent-Runtime)
  • RDS PostgreSQL 16 with pgvector
  • ElastiCache Redis for queues + session
  • Supabase Auth (SSR) shared across the suite
  • Stripe webhooks for billing events

Frontend

  • Next.js App Router (33 pages)
  • Tailwind CSS + shadcn/ui
  • Liquid Glass design system (Apple HIG)
  • CloudFront CDN distribution
  • WAF rate-limit + bot challenge

AI & Agents

  • Claude API for letter generation + voice coaching
  • 21 Shadow Team agents (tiered PR routing)
  • Agent-hub orchestrator with budget guardrails
  • 50-state legal citation database
  • python-docx formal document layout (exhibits, Bates stamps)

Infrastructure

  • Terraform-managed VPC + subnets + IAM
  • 123 cloud resources across 4 envs
  • Cloudflare Email Routing (28 addresses)
  • SendGrid transactional relay
  • GitHub Actions CI/CD with PR previews
Visit Live Site