START HERE — Neutral RITAPod™ v2.18
================================

Lens: neutral
Citation Contract grounding only — no plaintiff or defense strategic emphasis.

The RITAPod is the primary deliverable — a portable, grounded chronology for
any LLM. Formatted reports are optional; this file is the case intelligence.

De-identified chronology only. No identified patient data is included in this pod.
PHI was machine-verified before packaging.

Which path should I use?
------------------------

Path B — Local runner (recommended; true system-role injection)
  Run: python ritapod_runner.py  (or double-click AskRITAPod.bat on Windows)
  Best for: citation fidelity, consistent disclaimers, and repeatable Q&A
  without re-uploading each session.
  Know this: instructions.enc holds the same grounding guidelines as
  ai_system_prompt so the runner can inject them as a true system message
  (citation fidelity — NOT confidentiality). The runner ALSO prints the
  opening legal-advice disclaimer BEFORE the first model call — that part is
  hard-coded (not left to the model).

Path C — API (production / firm-hosted)
  python ritapod_runner.py --provider openai
  Set OPENAI_API_BASE, OPENAI_API_KEY, and OPENAI_MODEL (or Ollama vars).
  Best for: firm-hosted or BAA-covered endpoints, scripted workflows, and the
  same system-role injection as Path B.

Path A — Drop-and-go (quickest; best-effort web paste)
  Upload or paste DropMeInYourFavoriteAI.json into ChatGPT, Claude, Gemini, or a firm web LLM.
  Best for: a quick look or sharing with co-counsel on a model you already use.
  Know this: grounding guidelines are in the cleartext ai_system_prompt field
  (intentional — not a secret). Web UIs treat the whole file as a user
  message; answer quality depends on how closely the receiving model follows
  written context, which varies by model and can change over time.

Lens disclaimer
---------------
The export lens (Plaintiff, Defense, Expert Prep, or Neutral) sets DEFAULT
SUMMARY EMPHASIS ONLY — it is not advocacy AI and it is not a cage. The pod
answers any question the chronology supports, including opposing-side theories.
Ask directly; explicit questions always take precedence over lens defaults.

Suggested starter questions
-----------------------------
  - Summarize the documented clinical timeline with event citations.
  - What categories of care are absent from the extracted chronology?
Recommended (Path B — local runner)
-----------------------------------
1. Run python ritapod_runner.py (or double-click AskRITAPod.bat on Windows).
2. Ask your questions. Grounding is injected as a true system message, and the
   runner prints the legal-advice disclaimer before the first model turn.

Optional shortcut (Path A — web paste, best-effort)
---------------------------------------------------
1. Upload or paste DropMeInYourFavoriteAI.json into ChatGPT, Claude, Gemini, or a firm LLM.
   Reader blocks (field_map, query_battery, billing, care_gaps) are first;
   events[].raw_text is clipped. Full text is RITAPod_full.json.
2. Ask your questions. Citation quality depends on how closely the receiving
   model follows the baked-in ai_system_prompt guidelines.

RITAPod™ is a trademark of Precision Medical Legal Consulting, LLC. All rights reserved.
DropMeInYourCaseSystem.pdf is the same pod for systems that only take PDF (Filevine, Supio, and the like); its first page carries the hash of the JSON.

See GUIDE.txt for runner setup, PHI details, and production export requirements.
