Skip to main content
The single biggest mistake with a starter pack is to skip this step — to point it at your warehouse, decide it’s “close enough,” and ship. That bakes in decisions before you know which questions matter, and you get a model that’s 10% useful and 90% noise. This module is the antidote, and it takes 15 minutes.

​
0.1 · Answer one question

The North Star question — When this works, what does someone do differently on Monday morning?
Not “model all of healthcare.” Something narrow and real: “the actuarial team stops waiting three days for a PMPM cut,” or “care managers see open gaps for their panel every morning.” If you can’t name it yet, you’re not ready to build the ontology — you’re ready to have this conversation. Have it first.

​
0.2 · Pick the archetype that fits

Most healthcare engagements start from one of three North Stars. Pick the closest — it tells you which surfaces and terminology to lead with, and which to leave for later. (Full detail in the repo’s NORTH_STAR.md.)
ArchetypeForLead with
A · BI parity”Match the dashboards we already trust”cost_pmpm, utilization_per_1000, condition_prevalence + golden queries — reconcile first, govern second.
B · Care-gap / quality”Close gaps and move quality measures”hedis_measure, rx_adherence_pdc + value-set terminology.
C · Risk adjustment”Capture the risk we’re actually carrying”comorbidity_profile + CMS-HCC crosswalks + the HCC notes.

​
0.3 · You don’t fill anything out — Ana drafts it

There’s no questionnaire and no 50-question worksheet to work through. In Module 1, Ana looks at your actual data, asks a handful of sharp scoping questions, recommends the archetype that fits, and drafts your North Star (a short purpose statement plus the 6–8 questions it must answer in 30 days) as a reviewed north_star.md. Your job is to confirm or redirect — not to do homework here.
You’ll see: Next: Module 1 turns this into the written North Star the rest of the workshop builds toward.
Why the model gets cheaper as you use it — This isn’t just good practice — it’s the design. An agent that re-discovers your warehouse on every question pays an “amnesia tax” (most of its tokens go to rediscovery, and results aren’t reproducible). Reading a known model first and committing what it learns inverts that: discovery is paid once and amortized across every future question. See TextQL’s research, “Malleability Is All You Need” (VLDB 2026) — a measured ~30% token reduction and a model that gets more reliable the more it’s used.

​
✅ Checkpoint

  • You can state your North Star in one sentence
  • You picked an archetype (BI parity / care-gap / risk adjustment)
  • You know Module 1 is where Ana drafts your North Star from your data — no worksheet to fill out
Not sure which archetype? That is fine — in Module 1 Ana looks at your data and recommends one. You do not have to decide here.