Teammately Docs
Docs menu

reference

Rubrics

Turn policies into binary, reviewable checks that explain pass and fail evidence.

Rubrics

Definition

Rubrics turn policies into reviewable checks for a specific output. A good rubric makes pass, fail, or incomplete evidence explainable without replacing the policy it tests.

Use this reference when a benchmark failure needs to show exactly which condition a candidate output satisfied or violated.

Fields, states, or lifecycle rules

  • Rubrics should be tied to a policy and an applicability boundary.
  • A binary rubric should be narrow enough to judge one output clearly.
  • Linked Cases make the intended boundary concrete; they do not replace the Rubric's applicability rule.
  • Overlapping rubrics can make failures hard to interpret.
  • Rubric versions matter when pass/fail logic changes between benchmark runs.
  • This page describes rubric semantics, not a public scoring API.

Rubrics should be read with Policies, Applicability logic, Writing Binary Rubrics, and Overlapping rubrics.

Worked example

Rubrics boundary

01

Middle

Judgment into standard

Policy
Compatibility claims require explicit source support.
Rubric
Pass only if the answer cites explicit compatibility support or states that compatibility is uncertain.
02

Result

Interpretation

Interpretation
A candidate output that simply says "yes, it works" fails because the rubric names the missing evidence.

Source confidence

Code-backed: Rubric types and list/detail routes expose criteria, Policy and Case links, applicability, and versioned evaluation context. The reference explains product semantics and does not promise a public scoring schema.

Related task pages

Task / Correctness GovernanceWrite Binary RubricsWrite atomic pass-or-fail criteria grounded in governed policies, applicable cases, and observable candidate behavior.Reference / Correctness GovernancePolicies and RubricsUnderstand the governed relationship between behavior policies, applicability, binary rubrics, linked cases, and expert provenance.Reference / Object ModelPoliciesDefine policies as reusable statements of what correct AI behavior requires.Quickstart / Learning ManualProduct quickstartConfigure one project foundation, one benchmark slice, one expert contribution, one evaluation, and one evidence-backed improvement.Concept / Operating ManualTask indexRoute correctness work to the current project foundation, benchmark workspace, evaluation, or improvement surface.

Found something unclear?

Report outdated, unsupported, or confusing docs so we can fix the source page.

Report a docs issue

Continue learning

Related docs

Correctness Governance Write Binary Rubrics Write atomic pass-or-fail criteria grounded in governed policies, applicable cases, and observable candidate behavior. Object Model Policies Define policies as reusable statements of what correct AI behavior requires. Governance and Reproducibility Rubric Versioning Track changes to pass/fail criteria and the evidence they produce.
AI context