Skip to main content
Pin the scope —In every question below, name the entity and the source-of-truth tables. A plausible answer from the wrong (summary) table is worse than no answer — if two sources could answer, run both and let your SME rule which is truth.
Run each of these against your validated warehouse. For every answer, note that Ana cites the governed surface and shows the rendered SQL.

​
4.1 · Prevalence (the “diabetes question”)

Prompt
You’ll see: the whole ICD-10 branch handled by the grouper — one consistent, defensible number, not a guess over 70,000 codes.

​
4.2 · Cost PMPM

Prompt

​
4.3 · Readmissions

Prompt

​
4.4 · Utilization and risk

Prompt
You’ll see: utilization normalized the standard way, and risk wired to the official CMS HCC model — including the HCC hierarchy (trumping) and a by-HCC breakdown of what drives the score.
Know what RAF means here —The governed surface computes the diagnosis-driven HCC portion of RAF. The full CMS RAF adds demographic (age/sex) and interaction terms — which require demographic fields your eligibility data may not carry. Ana will say so rather than fabricate; the decision record in ontology/notes/ documents the scope.
Why everyone gets the same number —Metrics like PMPM and readmission can be computed several ways. The ontology pins one governed definition — with the decision recorded in ontology/notes/ — so Finance and Quality stop disagreeing.

​
4.5 · When the answer isn’t governed yet — watch the model grow

Now ask something from your shortlist that the starter doesn’t already cover. This is the important beat: a starter pack is a head start, not the finished model.
Prompt
You’ll see: Ana explore only the frontier (not re-derive the whole warehouse), answer, and propose a write-back — a new metric committed to your repo with provenance. Review and merge it, and the next person who asks gets the governed answer for free. That’s the malleable loop: the ontology you ship is the one you grow, and it gets more complete every time you use it.
You ratify; high-stakes definitions get review —Ana proposes; humans ratify via normal git review. Anything in governance-phi.md scope or a core metric should require review before merge (CODEOWNERS-style) — see STANDARDS.md. The point isn’t to let an agent rewrite your model unsupervised; it’s that discovered knowledge is captured instead of re-discovered next time.

​
✅ Checkpoint

  • All four question families answered through governed surfaces, SQL shown
  • You can point to the notes file explaining at least one metric’s definition decision
  • Ana proposed a write-back for a not-yet-governed question — and you saw it land as a PR