Attention: Create Scorecard

Create an Attention call scorecard for grading conversations, for one team or all teams.

Tool ID: attention_create_scorecard

Run this action

Use the TypeScript SDK for one call. Use ctx.tools.execute(...) inside a Play for durable calls, scheduled calls, or CSV processing.

import { Deepline } from 'deepline';

const deepline = await Deepline.connect();
const result = await deepline.tools.execute(
  'attention_create_scorecard',
  {
    "title": "VP of Engineering"
  },
);

console.log(result.toolResponse.raw);

CLI

deepline tools execute attention_create_scorecard --input '{
  "title": "VP of Engineering"
}' --json

Example response

The SDK returns this shape at result.toolResponse.raw. The example values illustrate the response.

{
  "data": {
    "data": {
      "uuid": "uuid_123",
      "title": "VP of Engineering",
      "organizationUUID": "organization_123",
      "allTeams": true,
      "enabled": true,
      "interactionType": "conversation",
      "expertMode": true,
      "isDefaultTemplate": true,
      "createdAt": "2026-01-15T12:00:00Z"
    }
  }
}

Use deepline describe attention_create_scorecard --json for the latest machine-readable contract.

Input reference

Payload for creating a scorecard template.

Name	Type	Required	Default	Details
`payload.title`	`string`	Yes	—	Human-readable title of the scorecard (1-128 characters, trimmed).
`payload.teamUUID`	`string`	No	—	UUID of the team to assign the scorecard to. Mutually exclusive with allTeams=true. Omit both for an unassigned scorecard.
`payload.allTeams`	`boolean`	No	`false`	Assign the scorecard to every team in the organization. Mutually exclusive with teamId.
`payload.enabled`	`boolean`	No	`true`	Whether the scorecard is active after creation.
`payload.interactionType`	`"conversation" \| "chat" \| "email"`	No	—	Type of interaction the scorecard evaluates. Allowed: `conversation`, `chat`, `email`.
`payload.detailedInstructions`	`string`	No	—	Optional free-form guidance (0-2000 characters).
`payload.scorecardPrompt`	`string`	No	—	Optional prompt override for expert mode (0-8000 characters).
`payload.expertMode`	`boolean`	No	`false`	Whether the scorecard uses custom prompts instead of the default template.
`payload.criteria`	`object`	No	—	Label-based criteria that gate when a scorecard is applied to an interaction.

Output reference

Standard tool result payload.

Name	Type	Required	Default	Details
`result.data`	`object`	Yes	—	Single-resource envelope wrapping a Scorecard.
`result.data.data`	`object`	Yes	—	A scorecard template used to evaluate a conversation, chat, or email.
`result.data.data.uuid`	`string`	Yes	—	Scorecard UUID.
`result.data.data.title`	`string`	Yes	—	Human-readable title of the scorecard (1-128 characters).
`result.data.data.organizationUUID`	`string`	Yes	—	UUID of the organization that owns the scorecard.
`result.data.data.teamUUID`	`string`	No	—	UUID of the specific team assigned to this scorecard, if any. Mutually exclusive with allTeams=true.
`result.data.data.allTeams`	`boolean`	Yes	—	Whether the scorecard is assigned to every team in the organization.
`result.data.data.enabled`	`boolean`	Yes	—	Whether the scorecard is active and runs against new interactions.
`result.data.data.interactionType`	`"conversation" \| "chat" \| "email"`	Yes	—	Type of interaction the scorecard evaluates. Allowed: `conversation`, `chat`, `email`.
`result.data.data.detailedInstructions`	`string`	No	—	Optional free-form guidance appended to the evaluator prompt.
`result.data.data.scorecardPrompt`	`string`	No	—	Optional prompt override used in expert mode.
`result.data.data.expertMode`	`boolean`	Yes	—	Whether this scorecard uses custom prompts (expert mode) instead of the default template.
`result.data.data.isDefaultTemplate`	`boolean`	Yes	—	Whether this scorecard was seeded as one of the default organization templates.
`result.data.data.criteria`	`object`	No	—	Label-based criteria that gate when a scorecard is applied to an interaction.
`result.data.data.criteria.operator`	`"AND" \| "OR"`	No	—	Boolean operator joining criteria conditions. Allowed: `AND`, `OR`.
`result.data.data.criteria.conditions`	`array`	No	—	List of field/value conditions evaluated with the operator.
`result.data.data.criteria.conditions[].field`	`string`	No	—	Field path being matched (for example, a label UUID or label option UUID).
`result.data.data.criteria.conditions[].value`	`string`	No	—	Expected value for the field to satisfy the condition.
`result.data.data.createdAt`	`string`	Yes	—	Timestamp when the scorecard was created. Format: `date-time`.
`result.meta`	`object`	No	—	Additional response metadata (status, paging).

Deepline cost

Pricing model: fixed (per call).
Estimated Deepline credits: 0 per pricing unit.
Provider-native pricing may still exist outside Deepline credit billing.

​Run this action

​CLI

​Example response

​Input reference

​Output reference

​Deepline cost

​Related documentation

Run this action

CLI

Example response

Input reference

Output reference

Deepline cost

Related documentation