mv.qa

Post-call QA scorecards and rubric. These methods are on mv.qa, where mv is your client (see the Node.js SDK). Each one returns the response object and throws when the API answers with an error.

`overrideScorecardItem()`

Override a scorecard item. Sets one rubric item’s score (0–5, or null for not applicable) as a supervisor would, or removes the override with clear: true. The call’s score and pass are recomputed; the change is in the scorecard’s history.

mv.qa.overrideScorecardItem(id: QaOverrideScorecardItemData["path"]["id"], itemKey: QaOverrideScorecardItemData["path"]["item_key"], body?: QaOverrideScorecardItemData["body"], options?: RequestOptions): Promise<QaOverrideScorecardItemResponse>

PATCH /calls/{id}/scorecard/items/{item_key} · API reference

Parameters

Name	Type	Required	Description
`id`	`string`	yes	A call ID (`call_…`).
`item_key`	`string`	yes	The rubric item’s key.
`body.clear`	`boolean`	no	true: remove the override (the model’s score applies again).
`body.note`	`string`	no	Why (shown in the scorecard’s history).
`body.score`	`number \| null`	no	The item’s score, 0–5 (half points round), or null for not applicable.
`options.headers["MoreVoice-Version"]`	`string`	no	The API version to use for this request. Defaults to the version the API key is pinned to.
`options`	`RequestOptions`	no	`idempotencyKey`, extra `headers` and an abort `signal`: see retries and idempotency.

Returns

Scorecard:

Field	Type	Description
`id`	`string`	The scorecard’s ID (one per call).
`object`	`"scorecard"`	Always `scorecard`.
`livemode`	`boolean`	`true` in live mode, `false` in test mode.
`call_id`	`string`	A call ID (prefix `call_`).
`status`	`"pending" \| "running" \| "done" \| "error" \| "skipped"`	`skipped`: too short to score (`error` says why); `error`: scoring failed.
`error`	`string \| null`	—
`score`	`number \| null`	0–100 after supervisor overrides (null: nothing applicable).
`model_score`	`number \| null`	0–100 as the model scored it.
`passed`	`boolean \| null`	—
`critical_failed`	`string[]`	Keys of the critical items that failed the call.
`rubric_source`	`"default" \| "copilot_profile" \| null`	Scored against the organisation’s rubric, or the call’s copilot profile’s.
`copilot_profile_id`	`string \| null`	`cop_…` ID.
`pass_threshold`	`number \| null`	—
`items`	`object[]`	One per rubric item.
`compliance`	`object \| null`	—
`disposition`	`"sale" \| "appointment" \| "callback_scheduled" \| "follow_up" \| "resolved" \| "unresolved" \| "not_interested" \| "escalated" \| … \| null`	—
`summary`	`string \| null`	—
`customer_sentiment`	`"positive" \| "neutral" \| "negative" \| "mixed" \| null`	—
`strengths`	`string[]`	—
`coaching`	`object[]`	—
`next_steps`	`string[]`	—
`objections`	`object[]`	—
`model`	`string \| null`	—
`created`	`string`	An ISO-8601 timestamp in UTC.
`updated`	`string`	An ISO-8601 timestamp in UTC.

Example

import MoreVoice from "@morevoice/sdk";

const mv = new MoreVoice(); // MOREVOICE_API_KEY from the environment

const scorecard = await mv.qa.overrideScorecardItem("call_7Hk2Lm9Qp", "item_key_123", {
  note: "Also asked about the decision maker.",
  score: 4,
});
console.log(scorecard);

`retrieveRubric()`

Retrieve the QA rubric. Returns the QaRubric object.

mv.qa.retrieveRubric(options?: RequestOptions): Promise<QaRetrieveRubricResponse>

GET /qa/rubric · API reference

Parameters

Name	Type	Required	Description
`options.headers["MoreVoice-Version"]`	`string`	no	The API version to use for this request. Defaults to the version the API key is pinned to.
`options`	`RequestOptions`	no	`idempotencyKey`, extra `headers` and an abort `signal`: see retries and idempotency.

Returns

QaRubric:

Field	Type	Description
`object`	`"qa_rubric"`	Always `qa_rubric`.
`livemode`	`boolean`	`true` in live mode, `false` in test mode.
`name`	`string`	—
`pass_threshold`	`number`	A call passes at this score (0–100) or above, with no critical item failed.
`items`	`object[]`	—
`builtin`	`boolean`	true: the built-in rubric (you have not saved your own).

Example

import MoreVoice from "@morevoice/sdk";

const mv = new MoreVoice(); // MOREVOICE_API_KEY from the environment

const qaRubric = await mv.qa.retrieveRubric();
console.log(qaRubric);

`retrieveScorecard()`

Retrieve a call’s QA scorecard. The call’s post-call QA scorecard. Calls are scored automatically when the organisation’s QA policy says so; 404 until one is.

mv.qa.retrieveScorecard(id: QaRetrieveScorecardData["path"]["id"], options?: RequestOptions): Promise<QaRetrieveScorecardResponse>

GET /calls/{id}/scorecard · API reference

Parameters

Name	Type	Required	Description
`id`	`string`	yes	A call ID (`call_…`).
`options.headers["MoreVoice-Version"]`	`string`	no	The API version to use for this request. Defaults to the version the API key is pinned to.
`options`	`RequestOptions`	no	`idempotencyKey`, extra `headers` and an abort `signal`: see retries and idempotency.

Returns

Scorecard:

Field	Type	Description
`id`	`string`	The scorecard’s ID (one per call).
`object`	`"scorecard"`	Always `scorecard`.
`livemode`	`boolean`	`true` in live mode, `false` in test mode.
`call_id`	`string`	A call ID (prefix `call_`).
`status`	`"pending" \| "running" \| "done" \| "error" \| "skipped"`	`skipped`: too short to score (`error` says why); `error`: scoring failed.
`error`	`string \| null`	—
`score`	`number \| null`	0–100 after supervisor overrides (null: nothing applicable).
`model_score`	`number \| null`	0–100 as the model scored it.
`passed`	`boolean \| null`	—
`critical_failed`	`string[]`	Keys of the critical items that failed the call.
`rubric_source`	`"default" \| "copilot_profile" \| null`	Scored against the organisation’s rubric, or the call’s copilot profile’s.
`copilot_profile_id`	`string \| null`	`cop_…` ID.
`pass_threshold`	`number \| null`	—
`items`	`object[]`	One per rubric item.
`compliance`	`object \| null`	—
`disposition`	`"sale" \| "appointment" \| "callback_scheduled" \| "follow_up" \| "resolved" \| "unresolved" \| "not_interested" \| "escalated" \| … \| null`	—
`summary`	`string \| null`	—
`customer_sentiment`	`"positive" \| "neutral" \| "negative" \| "mixed" \| null`	—
`strengths`	`string[]`	—
`coaching`	`object[]`	—
`next_steps`	`string[]`	—
`objections`	`object[]`	—
`model`	`string \| null`	—
`created`	`string`	An ISO-8601 timestamp in UTC.
`updated`	`string`	An ISO-8601 timestamp in UTC.

Example

import MoreVoice from "@morevoice/sdk";

const mv = new MoreVoice(); // MOREVOICE_API_KEY from the environment

const scorecard = await mv.qa.retrieveScorecard("call_7Hk2Lm9Qp");
console.log(scorecard);

`run.scorecard()`

Score a call. Scores the call against its rubric now, even when it is too short for automatic scoring, and answers the scorecard (it can take a few seconds). A call that already has a finished scorecard is not scored again unless force is true. 409 while the call is in progress.

mv.qa.run.scorecard(id: QaRunScorecardData["path"]["id"], body?: QaRunScorecardData["body"], options?: RequestOptions): Promise<QaRunScorecardResponse>

POST /calls/{id}/scorecard/run · API reference

Parameters

Name	Type	Required	Description
`id`	`string`	yes	A call ID (`call_…`).
`body.force`	`boolean`	no	Score again even when the call already has a finished scorecard (default false: it is returned as it is).
`options.headers["MoreVoice-Version"]`	`string`	no	The API version to use for this request. Defaults to the version the API key is pinned to.
`options.headers["Idempotency-Key"]`	`string`	no	A unique key (for example a UUID) that makes this request safe to retry: for 24 hours, a retry with the same key and parameters returns the first response instead of acting twice.
`options`	`RequestOptions`	no	`idempotencyKey`, extra `headers` and an abort `signal`: see retries and idempotency.

Returns

Scorecard:

Field	Type	Description
`id`	`string`	The scorecard’s ID (one per call).
`object`	`"scorecard"`	Always `scorecard`.
`livemode`	`boolean`	`true` in live mode, `false` in test mode.
`call_id`	`string`	A call ID (prefix `call_`).
`status`	`"pending" \| "running" \| "done" \| "error" \| "skipped"`	`skipped`: too short to score (`error` says why); `error`: scoring failed.
`error`	`string \| null`	—
`score`	`number \| null`	0–100 after supervisor overrides (null: nothing applicable).
`model_score`	`number \| null`	0–100 as the model scored it.
`passed`	`boolean \| null`	—
`critical_failed`	`string[]`	Keys of the critical items that failed the call.
`rubric_source`	`"default" \| "copilot_profile" \| null`	Scored against the organisation’s rubric, or the call’s copilot profile’s.
`copilot_profile_id`	`string \| null`	`cop_…` ID.
`pass_threshold`	`number \| null`	—
`items`	`object[]`	One per rubric item.
`compliance`	`object \| null`	—
`disposition`	`"sale" \| "appointment" \| "callback_scheduled" \| "follow_up" \| "resolved" \| "unresolved" \| "not_interested" \| "escalated" \| … \| null`	—
`summary`	`string \| null`	—
`customer_sentiment`	`"positive" \| "neutral" \| "negative" \| "mixed" \| null`	—
`strengths`	`string[]`	—
`coaching`	`object[]`	—
`next_steps`	`string[]`	—
`objections`	`object[]`	—
`model`	`string \| null`	—
`created`	`string`	An ISO-8601 timestamp in UTC.
`updated`	`string`	An ISO-8601 timestamp in UTC.

Example

import MoreVoice from "@morevoice/sdk";

const mv = new MoreVoice(); // MOREVOICE_API_KEY from the environment

const scorecard = await mv.qa.run.scorecard("call_7Hk2Lm9Qp", {
  force: false,
});
console.log(scorecard);

`updateRubric()`

Replace the QA rubric. Replaces the organisation’s rubric. Weights are relative, on one 0–100 scale (only the ratios count). Calls scored from now on use it; existing scorecards keep the rubric they were scored with.

mv.qa.updateRubric(body: QaUpdateRubricData["body"], options?: RequestOptions): Promise<QaUpdateRubricResponse>

PUT /qa/rubric · API reference

Parameters

Name	Type	Required	Description
`body.items`	`object[]`	yes	The items, in order; keys must be unique and at least one item needs a weight above 0.
`body.name`	`string`	no	Default: “Default QA rubric”.
`body.pass_threshold`	`number`	no	Default 70.
`options.headers["MoreVoice-Version"]`	`string`	no	The API version to use for this request. Defaults to the version the API key is pinned to.
`options`	`RequestOptions`	no	`idempotencyKey`, extra `headers` and an abort `signal`: see retries and idempotency.

Returns

QaRubric:

Field	Type	Description
`object`	`"qa_rubric"`	Always `qa_rubric`.
`livemode`	`boolean`	`true` in live mode, `false` in test mode.
`name`	`string`	—
`pass_threshold`	`number`	A call passes at this score (0–100) or above, with no critical item failed.
`items`	`object[]`	—
`builtin`	`boolean`	true: the built-in rubric (you have not saved your own).

Example

import MoreVoice from "@morevoice/sdk";

const mv = new MoreVoice(); // MOREVOICE_API_KEY from the environment

const qaRubric = await mv.qa.updateRubric({
  items: [
    {
      key: "discovery",
      label: "Discovery",
      weight: 60,
    },
    {
      key: "closing",
      label: "Next step",
      type: "boolean",
      weight: 40,
    },
  ],
  pass_threshold: 75,
});
console.log(qaRubric);