Who Can Ask What
Updated
AdvancedWhat you'll learn
~18 min- Explain why answer-level sensitivity can exceed every cited passage's
- Set a serving mode per question class, sized to the cost of a wrong or leaked answer
- Route the aggregation ruling to authority instead of deciding it in configuration
What it is: two decisions per question class, made by named owners before serving: who may ask, and whether answers go direct or as drafts for a human checker.
What it buys: the residual risk that Module 4 said survives every check lands somewhere chosen — on a checker for consequential classes, on a bounded audience for sensitive ones — instead of wherever the next question takes it.
What to fund: checker time for the classes that need it. That cost is the honest price of serving answers whose consequences exceed the evals’ guarantees, and it is much smaller than it sounds once the direct classes are carved off.
Prompt first: draft the serving matrix
Switch your workspace agent into plan mode and start with (if you do not have live exports or files handy, ask it to generate a small Meridian practice sample from the lesson’s scenario first):
Here are our question classes, access tiers, and evaluation results: [paste them]. Draft a serving matrix for the service owner to review and sign, and flag any class where synthesized answers aggregate sensitivity.Check that the plan or draft covers:
- Who may ask: the authorized audience for each question class enforced at the serving surface, not only inside retrieval.
- Recommended serving mode:
DIRECT(answers with citations go straight to the asker),DRAFT(answers route to a named checker for the claim-by-claim hand check before release), orBLOCKED(with the unblocking condition stated), justified by failure cost, leak cost, and evaluation history. - Aggregation flag: explicit flags on any class that can combine individually permitted passages into a synthesized answer more sensitive than any single source, routed to classification authority rather than resolved in config.
- Owner sign-off table: formatted as a decision table for the service owner to amend and sign.
If the draft recommends DIRECT for high-consequence classes or resolves aggregation risk on its own, follow up with: "Route consequential classes to DRAFT with a named checker, and flag any aggregation risk for classification authority instead of deciding it here."
The aggregation problem, transposed
If you took Building Trustworthy Data Products, you met the rule that two permitted inputs can join into something neither was cleared for. Answers do this too, and more fluently than any join. Ten field notes, individually all-staff, each mentioning one substation’s intermittent faults; the question “which substations have recurring unresolved faults?” produces an answer that is, functionally, a vulnerability map of the distribution system — a document nobody wrote, at a sensitivity no passage carries, assembled on demand.
Passage-level tiers cannot catch this: every citation checks out at all-staff. The control has to sit at the class level — which is why 1.3 bounded classes and why the prompt’s step 3 flags the classes whose answers aggregate. The ruling itself — is the aggregate a new sensitivity, and whose call is that — goes to the same authority that owns classification questions, with the flag and an example answer attached. The builder’s job is to notice and route, not to decide in a config file.
The serving mode is where residual risk lands
Module 4 ended with a promise: bound the consequence, don’t deny the residual. This is the bounding. Three modes, chosen per class by the cost of failure, not the maturity of the technology:
Direct — for classes where a wrong answer costs a recoverable nuisance and the evals are clean. The failure-history class: a wrong answer costs a supervisor a cross-check against a work order, the same check they perform on human answers.
Draft-for-checker — for classes where a wrong answer reaches a regulator, a customer, or a contract. The obligations class serves drafts: the answer plus citations lands with the contracts manager, who performs the ninety-second hand check before anything leaves. The system still saves the hours of finding; the human still owns the assertion. This mode is not a consolation prize — for consequential classes it is the designed end state, and teams that treat it as a stepping stone to direct are re-litigating 4.4’s limits with wishes.
Blocked — for classes that failed a gate, or whose aggregation ruling is pending. Stated as blocked, with the unblocking condition named, so it is a status and not a quiet death.
Direct mode’s convenience creates constant pressure: “the failure-history answers are instant, why does contracts take a day?” Because a wrong failure-history answer wastes a truck roll and a wrong obligations answer waives a claim — the modes differ because the consequences differ, and the matrix records that reasoning so it survives the third time the question is asked. Flattening to all-direct is undoing 4.4 by convenience; flattening to all-draft buries the checkers and kills the capability by queue.
Stop and escalate when a class’s aggregation flag is raised and no one holds authority over the aggregate’s sensitivity — the passage tiers had owners, but the synthesized answer is new territory, and inventing its classification in a serving config is the same unauthorized act as 2.3 warned against, one level up.
Every passage cited in an answer is all-staff, every citation opens, every claim grades supported. The answer itself maps which substations have recurring unresolved faults. What has the passage-level control missed?
Key takeaway
Answers aggregate: individually permitted passages synthesize into artifacts no passage’s tier anticipated, so who-may-ask is enforced per class at the serving surface, and aggregation flags route to classification authority instead of dying in a config file. The serving mode is where Module 4’s residual risk lands by design — direct where failure is a nuisance, draft-for-checker where it reaches a regulator or a contract, blocked with a named condition otherwise — recorded with its reasoning, because the pressure to flatten the matrix arrives weekly. Lesson 5.2 turns to the record the serving surface produces, which is a corpus of its own.
- LEADERSHIP DECISION
- sign the serving matrix - which classes answer directly, which draft for a checker - and fund the checker minutes the consequential classes cost
- PRACTITIONER ACTION
- prepare the matrix with eval history attached; flag aggregation classes to classification authority; never resolve sensitivity in config
- SUCCESS MEASURE
- every class serves in a signed mode; zero aggregation flags resolved by the builder; the matrix survives its weekly flattening pressure