A synthetic-data DRG validation copilot that helps a nurse reviewer work seeded DKA and Sepsis cases: chart and criteria side-by-side, four-section draft output, and an editable Pareo-safe internal note. Built from nearly 13 years as an ICU registered nurse plus hands-on AI workflow implementation. Gated behind Cloudflare Access — no real PHI, reviewer-in-the-loop, no automated overrides. Unattended demos use deterministic mock output; live OpenAI is for operator-hosted walkthroughs only.
DRG validation review is documentation-heavy, exception-heavy, and easy to get wrong under time pressure. Reviewers spend a large share of their time reading unstructured clinical narrative, cross-checking documentation against criteria, and manually tracking what has and has not been checked on a given case.
Tooling in this space tends to either (a) drop AI suggestions into a freeform interface with no workflow, or (b) automate hard decisions that should belong to a qualified reviewer. Both modes erode trust and create rework. The opportunity is the middle: structure the workflow, capture evidence as the reviewer moves through it, and keep the human as final authority.
A synthetic-data clinical validation assistant designed around the way a nurse reviewer actually works the case: surface the chart and criteria side-by-side, generate a four-section draft, and let the reviewer edit, save, and copy an internal note. Unattended demonstrations use deterministic mock output.
Every AI-assisted suggestion is treated as draft support content. The reviewer can edit the internal note and submit feedback. The nurse reviewer remains the final authority; saved drafts are not clinical, coding, or payment decisions.
The demo runs at drg-demo.twosevens.ai and is gated by Cloudflare Access. Visiting the URL directly will not grant access; reviewers must request approval first. Use the gateway below — that is where access requests are accepted.
The boundaries below are not aspirational — they are how the demo is actually run.
No real patient records, no protected health information, no de-identified production data. Cases are constructed for demonstration.
AI output is draft support content. A qualified nurse reviewer is the final authority on every disposition.
This is a demonstration surface. It is not a HIPAA-cleared production system and makes no PHI-readiness claim.
Exact-email allow-list managed by hand. External reviewers are added only after a request is submitted and reviewed.
The shape, not the secrets. No internal hostnames, no network-level identifiers, no Cloudflare Access policy IDs.
Next.js application that renders the reviewer surface and serves the validation workflow. Containerised for reproducible build and deploy.
Postgres holds synthetic case content, draft reviews, edited notes, and reviewer activity. The hosted demo is restricted to synthetic examples; real patient records must not be entered.
Cloudflare Access fronts the demo with an exact-email allow-list and a tunnel route. Approval is manual; nobody reaches the application surface without prior review.
Chart and criteria → four-section draft → reviewer edits and feedback. The demo records review activity; it does not make diagnosis, coding, payment, or reimbursement decisions.
The demo release is checked with tests, lint, type-checking, a production build, and a dependency audit. Browser checks exercise the reviewer workflow before deployment.
External reviewers only get access after an explicit approval. There is no public path to the live demo.
External reviewers receive access only after a request is submitted through the gateway and the email is added to the allow-list by hand.
Access requests are reviewed manually; no response-time commitment or automated provisioning is offered.
Approved reviewers see the synthetic-data demo only. Operator surfaces, configuration, and any internal tooling stay out of scope.
Reviewers, healthcare AI evaluators, and hiring teams: submit a request through the gateway. Access is granted by hand after a manual review of the request.
Request protected demo accessBackground — Why I can build this responsibly
I built this work from nearly 13 years as an ICU registered nurse, including about 11 years in travel nursing across multiple hospital systems. That background gives me a practical view of how clinical documentation, handoffs, staffing pressure, fragmented workflows, and operational risk actually show up on the floor.
I combine that clinical experience with hands-on work in AI-enabled workflow systems, distributed infrastructure, automation, and production-style software design. My focus is not replacing clinical judgment. It is building tools that reduce friction, preserve accountability, and keep humans in control of high-consequence decisions.
The same workflow discipline applied to adjacent problems — extraction-to-structured-output automation, workflow gating with evidence capture, and reliability practice on distributed operations.
Inconsistent source inputs become validated, structured outputs through extraction → normalization → validation → human review.
What the buyer gets
Workflow-heavy operations get staged state, required-action gates, evidence capture, and controlled closeout.
What the buyer gets
A private multi-node lab described through production-style repository controls: service separation, recoverability, and queue-backed execution.
What the buyer gets
What I bring to employer teams working on clinical AI, workflow redesign, and infrastructure-heavy automation.
I take on workflow audits, clinical AI implementation, and technical solutions engineering through scoped work with concrete artifacts.