{"query":"Case Review","corpusVersion":"local","generatedAt":"2026-09-13T04:37:20.927Z","results":[{"blockId":"coverage-management.case-review#case-review","pageId":"coverage-management.case-review","title":"Case Review","pageTitle":"Case Review","url":"https://teammately.ai/docs/coverage-management/case-review.md","humanUrl":"https://teammately.ai/docs/coverage-management/case-review#case-review","markdownUrl":"https://teammately.ai/docs/coverage-management/case-review.md","sectionId":"case-review","kind":"task","productArea":"coverage_management","score":915.452334748502,"reasons":["search_match","title_match","display_title_match","term_match"],"markdown":"# Case Review"},{"blockId":"coverage-management.case-review#review-candidates","pageId":"coverage-management.case-review","title":"Review candidates","pageTitle":"Case Review","url":"https://teammately.ai/docs/coverage-management/case-review.md","humanUrl":"https://teammately.ai/docs/coverage-management/case-review#review-candidates","markdownUrl":"https://teammately.ai/docs/coverage-management/case-review.md","sectionId":"review-candidates","kind":"task","productArea":"coverage_management","score":602.7067519278542,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Review candidates\n\nCandidates begin included for review. Remove a candidate when it is weak, redundant, misplaced, unsupported, or does not prove its tuple. Inspect its fit explanation, source and facet trace, input content, materials, and relationship to the tuple target. Inclusion should mean the candidate is suitable to enter the current benchmark set, not merely that generation succeeded.\n\nFor one tuple, **Generate more** appends candidates using count and operator instructions. **Regenerate** can reuse or synthesize source evidence, or run in synthesize-only mode. These actions have different provenance implications; preserve the displayed source relationship when deciding which candidate to keep."},{"blockId":"coverage-management.case-review#complete-the-review","pageId":"coverage-management.case-review","title":"Complete the review","pageTitle":"Case Review","url":"https://teammately.ai/docs/coverage-management/case-review.md","humanUrl":"https://teammately.ai/docs/coverage-management/case-review#complete-the-review","markdownUrl":"https://teammately.ai/docs/coverage-management/case-review.md","sectionId":"complete-the-review","kind":"task","productArea":"coverage_management","score":582.1679889245098,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Complete the review\n\nAccepted included candidates materialize into the benchmark's current Case set. Then inspect Dataset Representation and create a new Snapshot only after evaluator readiness and Snapshot blockers are clear. Existing Snapshots remain unchanged.\n\n{% example-demo title=\"Example: rejecting decorative evidence\" %}\nA tuple requires the candidate system to reconcile two contradictory tables. One prepared Case has a table that never affects the answer, while another requires comparing two columns and citing the newer record. The reviewer removes the decorative Case, verifies the second table, and admits only the candidate that proves the intended transformation.\n{% /example-demo %}"},{"blockId":"troubleshooting.unclear-cases#diagnose-the-case-not-the-reviewer","pageId":"troubleshooting.unclear-cases","title":"Diagnose the Case, not the reviewer","pageTitle":"Unclear Cases","url":"https://teammately.ai/docs/troubleshooting/unclear-cases.md","humanUrl":"https://teammately.ai/docs/troubleshooting/unclear-cases#diagnose-the-case-not-the-reviewer","markdownUrl":"https://teammately.ai/docs/troubleshooting/unclear-cases.md","sectionId":"diagnose-the-case-not-the-reviewer","kind":"error","productArea":"troubleshooting","score":480.31275933625494,"reasons":["search_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Diagnose the Case, not the reviewer\n\n1. Open the Case in its normal review presentation and read only what the assigned expert can see.\n2. Identify the judged input and output separately. For conversations, confirm the turn order and which response is under review.\n3. List every fact required to make the judgment, then verify each fact is present as Case content, context, source material, or an explicitly linked standard.\n4. Check whether metadata is being used as hidden instruction rather than visible context.\n5. Compare reviewer rationale. Repeated invented assumptions usually reveal the missing boundary."},{"blockId":"playbooks.coverage-gaps-before-review#review-readiness-trigger","pageId":"playbooks.coverage-gaps-before-review","title":"Review-readiness trigger","pageTitle":"Finding Coverage Gaps Before Review","url":"https://teammately.ai/docs/playbooks/finding-coverage-gaps-before-review.md","humanUrl":"https://teammately.ai/docs/playbooks/finding-coverage-gaps-before-review#review-readiness-trigger","markdownUrl":"https://teammately.ai/docs/playbooks/finding-coverage-gaps-before-review.md","sectionId":"review-readiness-trigger","kind":"recipe","productArea":"playbooks","score":409.9891610007443,"reasons":["search_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Review-readiness trigger\n\nUse this before a customer relies on Benchmark evidence for human review, especially when results are dominated by common Cases, a critical Rubric has few applicable Cases, or specialists identify behavior that the Dataset does not represent."},{"blockId":"benchmark-datasets.cases#review-before-snapshotting","pageId":"benchmark-datasets.cases","title":"Review before snapshotting","pageTitle":"Benchmark Dataset Cases","url":"https://teammately.ai/docs/benchmark-datasets/cases.md","humanUrl":"https://teammately.ai/docs/benchmark-datasets/cases#review-before-snapshotting","markdownUrl":"https://teammately.ai/docs/benchmark-datasets/cases.md","sectionId":"review-before-snapshotting","kind":"task","productArea":"benchmark_datasets","score":394.25242361153056,"reasons":["search_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Review before snapshotting\n\n1. Confirm each Case still conforms to Project Input Schema and has the intended materials.\n2. Inspect Coverage Facet assignments and source or contributor provenance.\n3. Check policy and rubric application, including whether eligible evaluator links are approved.\n4. Resolve missing or ambiguous output/reference mapping when the workflow requires reference outputs.\n5. Use Representation to check whether the set supports the intended claim.\n\n> Membership is not evidence yet\n>\n> The editable Cases tab can change. Use a Dataset Snapshot and Benchmark Version when an evaluation, comparison, or Improvement Session must remain reproducible."},{"blockId":"object-model.cases#definition","pageId":"object-model.cases","title":"Definition","pageTitle":"Cases","url":"https://teammately.ai/docs/object-model/cases.md","humanUrl":"https://teammately.ai/docs/object-model/cases#definition","markdownUrl":"https://teammately.ai/docs/object-model/cases.md","sectionId":"definition","kind":"reference","productArea":"object_model","score":386.22558388392775,"reasons":["search_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Definition\n\nCases are the behavior situations Teammately uses for review, coverage, and benchmark evidence. A case should preserve the input, source context, metadata, and version boundary needed to understand what behavior is being judged.\n\nUse this reference when a workflow depends on whether an example is reviewable, benchmark-ready, stale, duplicated, or missing the context a reviewer needs."},{"blockId":"integrations.import-case-examples#task-steps-import-case-examples","pageId":"integrations.import-case-examples","title":"Task steps: Import Case examples","pageTitle":"Import Case Examples","url":"https://teammately.ai/docs/integrations/import-case-examples.md","humanUrl":"https://teammately.ai/docs/integrations/import-case-examples#task-steps-import-case-examples","markdownUrl":"https://teammately.ai/docs/integrations/import-case-examples.md","sectionId":"task-steps-import-case-examples","kind":"task","productArea":"data_integrations","score":340.79440621597445,"reasons":["search_match","term_match","prefix_or_fuzzy_match"],"markdown":"### Task steps: Import Case examples\n\n1. Open Project Settings and inspect **Project Input Schema**. Confirm whether the Project expects plain text, chat, or structured input and which Case materials are required.\n2. Prepare a small representative sample. Separate the Case input from candidate output, human correction, and source-system bookkeeping.\n3. Open the Case import flow from the Project's Cases or Case Pool surface and upload the supported source file.\n4. Map source columns to input, named Case materials, and customer attributes. Do not map candidate output into Case input merely because it shares a row.\n5. Preview the normalized Cases. Inspect conversations, structured values, file associations, empty required fields, and duplicate source identifiers.\n6. Resolve validation and artifact-processing failures before admitting the full collection.\n7. Complete the import, then inspect the admitted Cases in Assets. Confirm Case identity, current version, source context, and material readiness.\n8. Add Cases to coverage or a Benchmark Dataset only after the team has reviewed whether they belong there."}]}