RITAPod™ · Demo Case

The Sutton case, ready to talk to.

A portable, de-identified chronology built from one synthetic case file — drop it into any AI assistant and start asking questions, citations included.

De-Identified
PHI Machine-Verified
Neutral Lens
Citation-Grounded
Get The Files

Two downloads, same case.

The source record RITA read, and the portable pod she built from it — grab one or both.

1

The Source Case File

The raw record RITA read — every report and the RITAPod below were built from this single file.

Download Case File (PDF) →
2

The RITAPod Package

The de-identified chronology, plus everything you need to run it — guides, a local runner, and the launcher script.

Download RITAPod (.zip) →
16
Clinical Events
3
Episodes
4
Identifiers Scrubbed
v2.9
RITAPod Version
Ask It Anything

How to drop it into an AI assistant.

The zip unpacks into one main file — DropMeInYourFavoriteAI.json — along with a printed guide and an optional local runner. The grounding and citation rules travel inside the file, so most of the time there's nothing else to paste.

On Your Computer

Fastest path — any web AI assistant

  1. Download and unzip ritapod-sutton.zip.
  2. Open ChatGPT, Claude, Gemini, or your firm's LLM in a browser.
  3. Start a new chat and attach or upload DropMeInYourFavoriteAI.json from the unzipped folder.
  4. Ask your first question — try one of the starters below.
For stronger citation fidelity (the assistant treats the grounding rules as a true system instruction instead of a pasted file), the package also includes a local runner: double-click AskRITAPod.bat on Windows, or run python ritapod_runner.py from the folder. That path needs Python 3.10+ installed and works great with a local model via Ollama.
On Your Phone

Talk to the case out loud

  1. Download ritapod-sutton.zip to your phone (or AirDrop/share it from your computer), then unzip it — most phones can do this from the Files app, or any cloud drive app (Files/Google Drive/Dropbox) that opens zip archives.
  2. Open your AI assistant's app — ChatGPT, Claude, or Gemini all support file uploads on mobile.
  3. Start a new chat and attach DropMeInYourFavoriteAI.json from your phone's files.
  4. If your assistant's app has a voice or "talk" mode, switch it on after the file is attached — you can then ask about the case out loud and hear the answers back, the same way you'd talk to a colleague who's read the file.
Voice mode depends on the AI app you're using having that feature — ChatGPT and Gemini's mobile apps currently support live voice conversations; check your assistant of choice if you're not sure. Either way, typed Q&A always works once the file is attached.
Try Asking

A few questions to start with.

Four kinds of questions the pod handles well — from a quick overview to strategy. We ran each of these against the actual pod before publishing them here.

Summary
Can you give me a case summary?
Find
Can you locate the date and report of any imaging studies?
Reasoning
Are there any gaps in the care, and what are the consequences?
Tactical
What weaknesses in this case could the defense use — and how might they be countered?
Questions like this get a strategic answer — the pod will remind you it isn't a lawyer and this isn't legal advice before it answers.

What's actually inside

This is the Neutral-lens RITAPod for the Sutton demo case — Citation Contract grounding only, no plaintiff or defense emphasis. The lens sets default summary emphasis, not a cage: ask a direct question and the pod will answer it either way, citations included.

Patient identifiers — name, DOB, MRN, SSN, phone, email — are scrubbed and machine-verified before packaging; export is blocked if residual patient PHI is detected. Provider and facility names are intentionally retained for litigation analysis. As with any case data, your firm remains responsible for HIPAA compliance and any vendor BAAs when it's used with a third-party AI service.

This is a synthetic demo case built to be shown, not a real patient record.