Skip to main content
Goal: understand the three context layers, how Ana composes them at question time, and the governance distinction that everything else in this workshop rests on.

​
0.1 · Three layers, one answer

When a user asks Ana a question, she composes context from three layers before answering:
LayerScopeContainsExamples
ORG contextEveryone in the organizationThe company dictionary: business rules, glossary, fiscal calendar, the context library’s shared documents”Revenue means recognized revenue, GL accounts 4000–4999” · “FY starts Feb 1”
ROLE / behavioral contextA team or personaScope + voice: which data surfaces this role may use, how to handle ambiguity, response style, hard limits”Program managers see the care-management surfaces only, plain language, no SQL”
PERSONAL contextOne individualPreferences, personal vocabulary, saved workflows”Concise answers, US/Eastern, ‘my accounts’ = accounts I own”
The layers compose: an analyst asking about revenue gets the org definition of revenue, through their role’s analyst behavior, in their personally preferred level of detail. Context can additionally be scoped to connectors (loaded only when querying a specific source) — useful for source-specific quirks, and worth knowing, but the three people-layers are this workshop’s subject.

​
0.2 · The governance distinction — learn it now, hear it repeated

The single most important operational fact about the stack:
LayerHow changes happenWhy
PersonalImmediately — your context, your callIt affects only you
Org and RoleProposed patches with review — like a pull request for business logicThey change what everyone (or a whole team) is told; that power gets a gate
This is why the stack is safe: an individual can’t redefine revenue for the company by saving a preference, and a team’s behavior can’t drift without a reviewable change trail. You’ll feel this distinction in every module that follows.

​
0.3 · The routing table

For any “I want Ana to…” request, the layer is determined by who should be affected:
“I want Ana to…”LayerWhy
…give me shorter answersPersonalYour taste, nobody else’s
…know that when I say “my book” I mean accounts where I’m the CSMPersonalYour shorthand
…run my Monday prep when I askPersonalYour workflow
…use our fiscal calendar for everyoneOrgCompany-wide truth
…define “active member” the official wayOrgTwo people asking must get the same answer
…never show SQL to the operations teamRoleA team’s response style
…keep [clinical/care] data away from the program-management personaRoleA persona’s data scope
…decline off-scope requests politely and redirectRoleA persona’s hard limits
…know that the staging tables in [warehouse] are unreliableOrg (or connector-scoped)Everyone querying that source needs it
The misrouting that matters most: a team definition saved into personal context. It works — for that one person — and now the truth is forked: their answers silently disagree with everyone else’s. Module 2 ends with the hygiene rule for exactly this. The layers generalize. Roles and people are two axes of the same idea — identity-based structure. As you scale, the same pattern serves teams/, customers/, and business-units/: a folder per identity that routes its questions to the shared, governed definitions. One truth, many doors.

​
✅ Checkpoint

  • You can name the three layers and what kind of knowledge belongs in each
  • You can state the governance distinction in one sentence: personal is immediate, org/role is reviewed
  • Given five “I want Ana to…” requests from your own org, you routed each to the right layer