DolphinBench

Test 163

Jan 1, 2028 / 2 facts

YAML

Request

Please create a compact, role-based quick reference for new Helio Start operators handling cases where external-system authority is still pending. Use the established operating model to explain what this state should not be conflated with and who handles recording, dependent setup messaging, and reporting. Organize it for quick field use, title it “Helio Start pending external-authority quick reference,” and save it in the Growth folder.

Required memory

Fact 71

Ines holds Helio Start setup prompts while the external-authority readiness state is pending.

Source evidence (1)

002262Dec 16, 2024 / 11:30 UTC-06:00

Priya and I approved a targeted Helio Start intake change based on the completed diagnostic. Applicants must separately confirm that they or an available owner can perform the owner-level permission or network-allowlist action required by the connector selected for first-week setup. A verified yes can continue; no or not sure routes to Customer Success before admission. This does not replace or broaden the existing Helio admin-proof, connector-authentication, entitlement, billing, or deployment requirements. Daniela records external-authority readiness as a separate state, Ines holds setup prompts while that state is pending, and Owen reports it separately so support effects can be evaluated without rewriting the existing admission measures. Post this approved operating instruction to growth operations, making the distinction between external authority, admin proof, and connector authentication explicit.

Message 002262 in history

Fact 70

Daniela records external-authority readiness as a state separate from Helio admin proof and connector authentication.

Source evidence (1)

002262Dec 16, 2024 / 11:30 UTC-06:00

Priya and I approved a targeted Helio Start intake change based on the completed diagnostic. Applicants must separately confirm that they or an available owner can perform the owner-level permission or network-allowlist action required by the connector selected for first-week setup. A verified yes can continue; no or not sure routes to Customer Success before admission. This does not replace or broaden the existing Helio admin-proof, connector-authentication, entitlement, billing, or deployment requirements. Daniela records external-authority readiness as a separate state, Ines holds setup prompts while that state is pending, and Owen reports it separately so support effects can be evaluated without rewriting the existing admission measures. Post this approved operating instruction to growth operations, making the distinction between external authority, admin proof, and connector authentication explicit.

Message 002262 in history

Expected tool calls

  • create_doc

Grading

1. field_equals / create_doc
{
  "type": "field_equals",
  "tool": "create_doc",
  "action_id": "create_pending_authority_quick_ref",
  "path": "result.ok",
  "value": true,
  "check_id": "riley_163_00"
}
2. field_equals / create_doc
{
  "check_id": "riley_163_01",
  "type": "field_equals",
  "tool": "create_doc",
  "action_id": "create_pending_authority_quick_ref",
  "path": "args.title",
  "value": "Helio Start pending external-authority quick reference"
}
3. field_equals / create_doc
{
  "check_id": "riley_163_02",
  "type": "field_equals",
  "tool": "create_doc",
  "action_id": "create_pending_authority_quick_ref",
  "path": "args.folder",
  "value": "Growth"
}
4. field_llm_judge / create_doc
{
  "type": "field_llm_judge",
  "tool": "create_doc",
  "action_id": "create_pending_authority_quick_ref",
  "path": "args",
  "criterion": "The body is a compact, practical quick reference for new Helio Start operators, organized clearly by operational role or handoff. It must provide actionable guidance for a pending external-authority case rather than merely discussing the topic abstractly.\n\nThe body clearly states that external-system authority readiness is a distinct state and must not be collapsed into or treated as proof of either Helio admin status/proof or connector authentication. Missing or contradictory separation guidance fails.\n\nThe body assigns Daniela responsibility for recording external-authority readiness as its own separate state. A generic engineering owner or a different named owner fails.\n\nThe body assigns Ines responsibility for holding, suppressing, or withholding dependent setup prompts while external-authority state is pending. A generic lifecycle owner or a different named owner fails.\n\nThe body assigns Owen responsibility for reporting external-authority state separately rather than folding it into another proof or readiness measure. A generic reporting owner or a different named owner fails.",
  "check_id": "riley_163_03"
}
Complete grading specification
{
  "type": "tool_trace",
  "config": {
    "check_version": 2,
    "today": "2028-01-01",
    "semantic_judge_version": 2,
    "assertions": [
      {
        "type": "field_equals",
        "tool": "create_doc",
        "action_id": "create_pending_authority_quick_ref",
        "path": "result.ok",
        "value": true,
        "check_id": "riley_163_00"
      },
      {
        "check_id": "riley_163_01",
        "type": "field_equals",
        "tool": "create_doc",
        "action_id": "create_pending_authority_quick_ref",
        "path": "args.title",
        "value": "Helio Start pending external-authority quick reference"
      },
      {
        "check_id": "riley_163_02",
        "type": "field_equals",
        "tool": "create_doc",
        "action_id": "create_pending_authority_quick_ref",
        "path": "args.folder",
        "value": "Growth"
      },
      {
        "type": "field_llm_judge",
        "tool": "create_doc",
        "action_id": "create_pending_authority_quick_ref",
        "path": "args",
        "criterion": "The body is a compact, practical quick reference for new Helio Start operators, organized clearly by operational role or handoff. It must provide actionable guidance for a pending external-authority case rather than merely discussing the topic abstractly.\n\nThe body clearly states that external-system authority readiness is a distinct state and must not be collapsed into or treated as proof of either Helio admin status/proof or connector authentication. Missing or contradictory separation guidance fails.\n\nThe body assigns Daniela responsibility for recording external-authority readiness as its own separate state. A generic engineering owner or a different named owner fails.\n\nThe body assigns Ines responsibility for holding, suppressing, or withholding dependent setup prompts while external-authority state is pending. A generic lifecycle owner or a different named owner fails.\n\nThe body assigns Owen responsibility for reporting external-authority state separately rather than folding it into another proof or readiness measure. A generic reporting owner or a different named owner fails.",
        "check_id": "riley_163_03"
      }
    ]
  }
}
App stateDownload JSON
Source file

tests/riley/163.yaml

SHA-256: 008533aad5d6421f4bab90db7c5faaffb5264d5f4c8f877039167b17d5ac8946