Skip to main content
The single biggest mistake with a starter pack is to skip this step — to point it at your custody 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 wealth management.” Something narrow and real: “the COO stops waiting a week for the firm-wide net-flows number,” or “every advisor sees the concentrated positions in their book before the quarterly review.” 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 wealth / asset-management engagements start from one of three North Stars. Pick the closest — it tells you which surfaces, classification, and governance 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 AUM, flows, and book numbers we already report”aum, net_flows, advisor_book, effective_fee_rate + golden queries — reconcile first, govern second.
B · Portfolio risk & concentration”Find the exposure before it finds us”concentration_risk, asset_allocation, benchmark_relative_return + the classification layer.
C · Household rollup & suitability”Report at the relationship, not the account”advisor_book, client_attrition, aum by segment + identity-resolution.md and MNPI/PII governance.

​
0.3 · Let Ana write it down (next module)

You don’t pick from a question bank or fill out a worksheet. In Module 1 you let Ana look at your actual data, run a short scoping conversation, and draft your North Star — one paragraph on what the ontology is for, plus the 6-8 questions it must answer in 30 days — saved as north_star.md and proposed as a reviewed change. The archetypes above are examples to spark yours, not a menu; Ana recommends one from what it sees.
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 know the three archetypes (BI parity / risk & concentration / household rollup) — examples to spark yours, not a menu
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.