> ## Documentation Index
> Fetch the complete documentation index at: https://docs.textql.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Start with Your North Star

> 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 kno… (~15 min)

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

<Note>
  **The North Star question** — **When this works, what does someone do differently on Monday morning?**
</Note>

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`](https://github.com/TextQLLabs/ontology-starter-kits/blob/main/healthcare/NORTH_STAR.md).)

<table>
  <tr><th>Archetype</th><th>For</th><th>Lead with</th></tr>
  <tr><td>**A · BI parity**</td><td>"Match the dashboards we already trust"</td><td>`cost_pmpm`, `utilization_per_1000`, `condition_prevalence` + golden queries — reconcile *first*, govern second.</td></tr>
  <tr><td>**B · Care-gap / quality**</td><td>"Close gaps and move quality measures"</td><td>`hedis_measure`, `rx_adherence_pdc` + value-set terminology.</td></tr>
  <tr><td>**C · Risk adjustment**</td><td>"Capture the risk we're actually carrying"</td><td>`comorbidity_profile` + CMS-HCC crosswalks + the HCC notes.</td></tr>
</table>

## 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.

<Check>
  **You'll see:** **Next:** Module 1 turns this into the written North Star the rest of the workshop builds toward.
</Check>

<Note>
  **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.
</Note>

### ✅ 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.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.