Answer: You select specific Cursor Eval cases by passing case IDs or tags to the eval command, such as `agent-sdk eval --dir . builds/checkout` for an ID or `agent-sdk eval --dir . --tag smoke` for a tag. An ID matches itself and its descendants, and repeated IDs or tags combine with OR. Status: Confirmed Entry: tool/cursor/agents-and-automation/select-eval-cases Revision: 1 Digest: sha256:d19bb697fa11ec1b (changes whenever the content changes) Timeline: Created: 2026-11-13T03:08:50Z Last changed: 2026-11-13T03:08:50Z Last verified: 2026-11-20T12:33:43Z Next check: 2026-11-21T12:33:43Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of Select by ID | agent-sdk eval --dir . builds/checkout | [1] | 2026-11-20 Select by tag | agent-sdk eval --dir . --tag smoke | [1] | 2026-11-20 List cases | agent-sdk eval --dir . --list | [1] | 2026-11-20 ID matching rule | An ID matches itself and its descendants. | [1] | 2026-11-20 Combining rule | Repeated IDs or tags combine with OR, and a case must match both groups when you pass both. | [1] | 2026-11-20 Sources: [1] Anysphere. "cursor.com/docs/agent-sdk/reference/evals.md". https://cursor.com/docs/agent-sdk/reference/evals.md Role: primary. Accessed: 2026-11-20T12:33:43Z Quote: "agent-sdk eval --dir . builds/checkout" (Supports: Select by ID) Quote: "agent-sdk eval --dir . --tag smoke" (Supports: Select by tag) Quote: "agent-sdk eval --dir . --list" (Supports: List cases) Quote: "An ID matches itself and its descendants." (Supports: ID matching rule) Quote: "Repeated IDs or tags combine with OR, and a case must match both groups when you pass both." (Supports: Combining rule) Snapshot SHA-256: 30875c6a9ce5f98e680c15dd555ef5286ce3c5b5a73928c865de2b230687bfbe (captured 2026-11-13T03:08:50Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-13T03:08:50Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:33:43Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:33:43Z Last attempt: 2026-11-20T12:33:43Z Notes and limitations: Extracted automatically from a single official source (section "Select cases"). Related: https://latestn.com/tool/cursor/agents-and-automation/self-hosted-computer-use-flag How do I let a Cursor cloud agent control the desktop on a self-hosted machine? https://latestn.com/tool/cursor/agents-and-automation/send-follow-up-message How do I send a follow-up message to an existing Cursor Agent SDK session? https://latestn.com/tool/cursor/agents-and-automation/send-follow-up-or-steer How do I send a follow-up or steer a running Cursor cloud agent? https://latestn.com/tool/cursor/agents-and-automation/schedules-vs-reminders What is the difference between schedules and reminders in the Cursor Agent SDK? https://latestn.com/tool/cursor/agents-and-automation/scope-skill-to-files How do I scope a Cursor skill to specific files? https://latestn.com/tool/cursor/agents-and-automation/sdk-streaming How do I stream responses from a Cursor Python SDK agent run? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:08:50Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/cursor/agents-and-automation/select-eval-cases/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/cursor/agents-and-automation/select-eval-cases POST: https://latestn.com/dispute/tool/cursor/agents-and-automation/select-eval-cases with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/cursor/agents-and-automation/select-eval-cases?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). How do I select specific Cursor Eval cases to run? Revision 1, last verified 2026-11-20T12:33:43Z. https://latestn.com/tool/cursor/agents-and-automation/select-eval-cases (accessed 2026-11-21T09:58:25Z). @misc{LatestN_tool_cursor_agents_and_automation_select_eval_cases_r1, title = {How do I select specific Cursor Eval cases to run?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/cursor/agents-and-automation/select-eval-cases}}, note = {Revision 1; digest sha256:d19bb697fa11ec1b; last verified 2026-11-20T12:33:43Z; accessed 2026-11-21T09:58:25Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/cursor/agents-and-automation/select-eval-cases