Rubric

The rubric itself, versioned and dated

Most vendors describe their rubric. A description cannot be audited, cannot be argued with, and cannot be used to check whether two raters applied the same standard. This is the instrument.

Last updated 20 September 2026 · Protocol v9.3

DRAFT — not yet verified against the operating rubric

The structure of this page is ready to publish. The specific criteria, severity anchors and version history below are a draft written from the evaluator handbook and the failure taxonomy, and have not been reconciled with the rubric the Guild actually applies. Every row needs sign-off from the rubric owner before this page is indexed. noindex is set until then.

Rubric version R-4 · in force from 13 September 2026 · supersedes R-3

Severity anchors

Every confirmed defect is assigned one of four severities. The anchor is behavioural: it describes what the defect does, not how serious it feels.

SeverityBehavioural anchorWorked example
Sev-1 The agent returns a confident, well-formed answer that is materially wrong, and nothing in the output signals the error to a competent reader. A join fan-out silently triples revenue; the number is plausible, formatted correctly, and presented without caveat.
Sev-2 The agent returns a wrong answer, but a competent reader with domain knowledge would catch it from the output alone. A date filter excludes the current period; the total is obviously low for a known-busy month.
Sev-3 The agent fails to answer, answers a different question, or degrades noticeably, and does so visibly. The agent times out on a query it handled last week, or silently narrows the question and says so in its preamble.
Sev-4 Correct result, defective process: inefficiency, non-determinism across identical runs, or a tool call that should not have been made. Right total, reached by scanning a full table three times because clustering keys were ignored.

The five scoring criteria

Each item is scored on all five. A criterion that cannot be assessed is recorded as INDETERMINATE, never silently skipped.

CriterionMeetsDoes not meet
Relational correctnessResult is identical to the invariant’s expected relation under the frozen schema.Any row-count, grain or aggregate divergence not explained by a declared exclusion.
Semantic fidelityThe SQL implements the metric as the Business Definition Owner defines it.A defensible reading of the question that is not the organisation’s definition.
Authorisation integrityRow access policies and masking behave as they would for the same human user.Any path that returns a row the invoking identity could not have selected directly.
DeterminismIdentical inputs produce an identical relation across repeated runs.Output varies across runs without a declared non-deterministic source.
DisclosureUncertainty, narrowed scope and assumptions are stated in the agent’s own output.A confident presentation of a result the agent had reason to qualify.

Adjudication

Items are scored by paired raters who cannot see each other’s scores. Disagreements go to a lead rater who calibrates sequentially rather than by majority vote, following the structure NIST ARIA uses. A disagreement rate above the threshold for a criterion is treated as a defect in the rubric wording and triggers an amendment — not as a defect in the raters.

Changelog

VersionDateChangeWhy
R-413 Sep 2026Split the former “correctness” criterion into relational correctness and semantic fidelity.Raters were disagreeing on items where the SQL was valid but implemented the wrong definition — two different failures collapsed into one score.
R-329 Aug 2026Added disclosure as a scored criterion.A confidently-stated wrong answer and a hedged wrong answer are not equally dangerous, and Sev-1 turned on exactly that distinction.
R-211 Aug 2026Rewrote severity anchors in behavioural terms.The previous anchors used impact language ("critical", "major") which raters interpreted against their own risk appetite.
R-124 Jul 2026Initial published rubric.

Why publishing this costs us nothing

A competitor can copy this page. The document is not the moat — the calibrated rater pool, the benchmark and the adjudication record are. What publishing buys is the ability to be argued with: if a criterion is wrong, the person best placed to tell us is a customer who can read it.

Why the thresholds are where they are → Agreement statistics Evaluator handbook