7 AI apps built. 5 in production.

Every app here carries its real stage. I built seven of them at work for a national healthcare data company: five run in production, Enterprise Platform MCP is in development, and Stress Tester is a delivered prototype. An eighth from that job, the Observability & Governance Engine, has its first stage built. The rest are my independent work.

1. Intake layer

   AI Use Case Submission Platform

   Intake for AI tool ideas: each one is screened for patient data first, and the ideas it clears are scored against a weighted rubric, with a reason for every rating, and ranked before the review meeting.ProductionBuilt at work for a national healthcare data company
2. Retrieval layer

   RFP Assist

   Drafts RFP responses from the company's Loopio answer library, with reviewer approval on every answer.ProductionBuilt at work for a national healthcare data company
3. Signal agents layer

   Payer Churn Signal App

   Combines Gainsight, Salesforce, and ServiceNow data with AI agents that scan the news for M&A signals, then alerts account teams to at-risk clients.ProductionBuilt at work for a national healthcare data company
4. PII gate layer

   LawLynx

   A multi-agent legal platform with 51 specialized AI agents and a PII gate in front of every external model.In developmentIndependent platform, pre-beta
5. Model router layer

   Command Center OS

   My own AI operations platform. It runs several AI coding tools side by side, sends each job to the cheapest engine that can do it, keeps a shared memory, and waits for my approval before anything goes out.In developmentMy own system. Runs locally today; moves to a VPS when finished
6. Test harness layer

   Application Testing Engine

   Runs on every pull request in Azure DevOps and sends the team a detailed report.ProductionBuilt at work for a national healthcare data company
7. Telemetry layer

   Observability & Governance Engine

   An engine that sits between an organization's AI applications and the model providers. It records every AI call with the exact data versions behind it.Built, stage oneDesigned at work for a national healthcare data company
8. Audit ledger layer

   PresidioFlow

   Repairs records that regulated data pipelines reject, and records every fix in a hash-chained audit ledger.PrototypeIndependent platform
9. Library layer

   Prompt, Skill & Agent Library

   A company-wide library of prompts, Skills, skill chains, and agents, with peer voting to keep the most helpful.ProductionBuilt at work for a national healthcare data company
10. Also built

    Contractor PM Platform

    A project management and estimating platform I built for a specialty contractor. It is complete and ready for its first users.CompleteReady for its first users
11. Also built

    Cloud CLI Command Forge

    A Next.js web app I built that turns plain-English requests into AWS, Azure, and Google Cloud CLI commands and Terraform, using an AI model. A teammate and I used it to cut weeks of Azure work down to a couple of days. It stayed private, shared through a temporary preview link, and was never published.PrototypeMy own project
12. Also built

    Stress Tester

    A load testing tool for internal applications, built in one session as an MVP for another development team, with real and demo modes, pluggable auth, and full handoff docs.PrototypeBuilt at work for a national healthcare data company
13. Also built

    Enterprise Platform MCP

    Gives AI assistants safe, controlled access to a large healthcare data platform through one shared core, four adapters, and 13 tools, with a person approving before anything is promoted to production.In developmentBuilt at work for a national healthcare data company