Skip to content

Prompts

The questions an audit asks the AI surfaces. Generated from the brand profile, then reviewed and selected. Beta: these shapes may change; see the changelog.

GET /audits/{auditId}/prompts

The prompt set with its selection state. ready is true when the audit is waiting for prompt review, and maxQueries is the plan’s ceiling on how many may be selected — selecting more than that is rejected when the run starts, not here.

Terminal window
curl "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts" \
-H "Authorization: Bearer $BEKET_API_KEY"
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
successbooleanyes
dataPromptSetyes
{
"success": true,
"data": {
"ready": false,
"status": "COMPLETED",
"prompts": [
{
"id": "0f4d5c46-b98e-4854-af39-2f6c7a32c038",
"text": "best widget software for small teams",
"selected": true,
"angleId": "CUSTOM",
"language": null,
"promptType": "UNBRANDED",
"topicId": null,
"region": null,
"querySubject": "OFFERING",
"funnelStage": null,
"angleLabel": "Custom",
"isCustom": true,
"branded": false
},
{
"id": "a3985077-683f-4df2-9b51-6474baab91e2",
"text": "how do I choose a widget vendor",
"selected": true,
"angleId": "CUSTOM",
"language": null,
"promptType": "UNBRANDED",
"topicId": null,
"region": null,
"querySubject": "OFFERING",
"funnelStage": null,
"angleLabel": "Custom",
"isCustom": true,
"branded": false
}
],
"maxQueries": 25
}
}

POST /audits/{auditId}/prompts

Adds one prompt you wrote (3–500 characters). It is selected when the plan has room and lands unselected otherwise — an add is never refused for capacity. It starts under the CUSTOM angle and is moved to a better-fitting angle in the background, so a later read may show a different angleId.

selectedIds is optional: send it to replace the selection of existing prompts in the same transaction as the add — the way to make room on a plan whose minimum and maximum selection are equal, where a separate deselect would be refused. Omit it to leave the selection alone.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text":"<text>"}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
textstringyes
selectedIdsstring[]
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.promptobjectyes
data.prompt.idstringyes
data.prompt.textstringyes
data.prompt.selectedbooleanyes
data.prompt.angleIdstringyes
data.prompt.angleLabelstring
data.prompt.querySubjectstring
data.prompt.funnelStagestring | null
data.prompt.isCustombooleanyes
data.prompt.brandedbooleanAbsent when the phrasing could not be classified.
data.prompt.languagestring
{
"success": true,
"data": {
"prompt": {
"id": "c4fdd333-0f2f-49d4-9ccf-5740eae5d56b",
"text": "which widget tools integrate with spreadsheets",
"querySubject": "OFFERING",
"funnelStage": null,
"selected": true,
"angleId": "CUSTOM",
"angleLabel": "Custom",
"isCustom": true,
"branded": false,
"language": "EN"
}
}
}

DELETE /audits/{auditId}/prompts/{promptId}

Takes the prompt out of the set. A prompt that has already been answered is archived rather than deleted, so its history stays in past snapshots; removed says which happened. Either way it no longer appears in the list.

Terminal window
curl -X DELETE "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/PROMPT_ID" \
-H "Authorization: Bearer $BEKET_API_KEY"
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
promptIdpathyesstringThe prompt’s id.
FieldTypeRequiredDescription
successbooleanyes
dataPromptRemovalyes
{
"success": true,
"data": {
"prompts": [
{
"id": "0f4d5c46-b98e-4854-af39-2f6c7a32c038",
"text": "best widget software for small teams",
"selected": true,
"angleId": "CUSTOM",
"language": null,
"promptType": "UNBRANDED",
"topicId": null,
"region": null,
"querySubject": "OFFERING",
"funnelStage": null,
"angleLabel": "Custom",
"isCustom": true,
"branded": false
},
{
"id": "a3985077-683f-4df2-9b51-6474baab91e2",
"text": "how do I choose a widget vendor",
"selected": true,
"angleId": "CUSTOM",
"language": null,
"promptType": "UNBRANDED",
"topicId": null,
"region": null,
"querySubject": "OFFERING",
"funnelStage": null,
"angleLabel": "Custom",
"isCustom": true,
"branded": false
}
],
"maxQueries": 25,
"removed": "deleted"
}
}

POST /audits/{auditId}/prompts/{promptId}/dismiss

Removes a prompt found in search results (mined: true) and remembers the dismissal, so the next run does not find it again. Other prompts are removed with DELETE /audits/{auditId}/prompts/{promptId}.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/PROMPT_ID/dismiss" \
-H "Authorization: Bearer $BEKET_API_KEY"
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
promptIdpathyesstringThe prompt’s id.
FieldTypeRequiredDescription
successbooleanyes
dataPromptRemovalyes

POST /audits/{auditId}/prompts/{promptId}/edit

Changes a prompt’s text. An unanswered prompt is edited in place. An answered one is archived with its history and a new prompt takes its place, keeping its selection: the response’s id is then the new prompt and parentId the old one, otherwise null.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/PROMPT_ID/edit" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"text":"<text>"}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
promptIdpathyesstringThe prompt’s id.
FieldTypeRequiredDescription
textstringyes
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.idstringyes
data.parentIdstring | nullyes
data.selectedbooleanyes
{
"success": true,
"data": {
"id": "c4fdd333-0f2f-49d4-9ccf-5740eae5d56b",
"parentId": null,
"selected": true
}
}

PATCH /audits/{auditId}/prompts/{promptId}/language

Changes the language a prompt is asked in. A prompt that has been answered is replaced rather than changed, so its history stays in past snapshots: the response’s id is then the new prompt and replacedPromptId the old one.

Terminal window
curl -X PATCH "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/PROMPT_ID/language" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"language":"<language>"}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
promptIdpathyesstringThe prompt’s id.
FieldTypeRequiredDescription
languagestringyesOne language, as a name or an ISO 639-1 code (French, FR). Stored as the uppercase code; anything else is a 400.
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.idstringyes
data.languagestringyes
data.replacedPromptIdstring | nullyes
data.selectedbooleanyes
{
"success": true,
"data": {
"id": "c4fdd333-0f2f-49d4-9ccf-5740eae5d56b",
"language": "EN",
"replacedPromptId": null,
"selected": true
}
}

PATCH /audits/{auditId}/prompts/{promptId}/type

Overrides the classifier’s branded/unbranded call. promptTypeSource becomes user, so a later reclassification leaves it alone. RECALL is fixed: no prompt moves into or out of it.

Terminal window
curl -X PATCH "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/PROMPT_ID/type" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"promptType":"<promptType>"}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
promptIdpathyesstringThe prompt’s id.
FieldTypeRequiredDescription
promptType“UNBRANDED” | “BRANDED” | “RECALL”yes
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.idstringyes
data.promptType“UNBRANDED” | “BRANDED” | “RECALL”yes
data.promptTypeSource“classifier” | “user”yes
{
"success": true,
"data": {
"id": "c4fdd333-0f2f-49d4-9ccf-5740eae5d56b",
"promptType": "BRANDED",
"promptTypeSource": "user"
}
}

POST /audits/{auditId}/prompts/actions

Applies one action — select, deselect, remove, restore — to up to 500 prompts, and reports what happened to each. remove archives a prompt that has been answered and deletes one that has not; removed counts both.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/actions" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"action":"<action>","queryIds":[]}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
action“select” | “deselect” | “remove” | “restore”yes
queryIdsstring[]yesPrompt ids. Repeats collapse; an id that is not a prompt of this audit is answered not_found.
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.action“select” | “deselect” | “remove” | “restore”yes
data.resultsobject[]yes
data.results[].idstringyes
data.results[].outcome“changed” | “unchanged” | “not_found” | “duplicate” | “archived”yes
data.removedobject
data.removed.archivedintegeryes
data.removed.deletedintegeryes
data.capacityPromptCapacityyes
{
"success": true,
"data": {
"action": "select",
"results": [
{
"id": "0f4d5c46-b98e-4854-af39-2f6c7a32c038",
"outcome": "unchanged"
},
{
"id": "a3985077-683f-4df2-9b51-6474baab91e2",
"outcome": "unchanged"
}
],
"capacity": {
"used": 3,
"cap": 25,
"left": 22
}
}
}

POST /audits/{auditId}/prompts/bulk

Adds up to 100 prompts in one request, one per entry in texts. Each line is cleaned the way the dashboard’s paste box cleans it (list markers, numbering and surrounding quotes are stripped). If any line is out of bounds the whole request is a 400 naming every bad line, and nothing is added. Duplicates — within the list or of a prompt already on the audit — are skipped and counted in skippedDuplicates, so sending the same list twice is safe.

New prompts are selected while the plan has room. selectedIds is optional: send it to replace the selection of existing prompts in the same transaction as the add — the way to make room on a plan whose minimum and maximum selection are equal, where a separate deselect would be refused. Omit it to leave the selection alone. selectedIds: [] deselects every existing prompt.

Send returnPrompts: false to receive only the counts: the full list can run to tens of kilobytes, and an automation rarely needs it.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/bulk" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"texts":[]}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
textsstring[]yes
selectedIdsstring[]
returnPromptsboolean
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.promptsPrompt[]
data.maxQueriesinteger | nullyes
data.addedintegeryes
data.selectedintegeryesHow many of the added prompts were selected.
data.skippedDuplicatesintegeryes
{
"success": true,
"data": {
"maxQueries": 25,
"added": 2,
"selected": 2,
"skippedDuplicates": 0
}
}

GET /audits/{auditId}/prompts/export.csv

Every prompt, active and archived, as a CSV download whose headers the import accepts. Past 5000 rows the file ends with a # truncated line; page the rest with GET /audits/{auditId}/prompts/manage.

Terminal window
curl "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/export.csv" \
-H "Authorization: Bearer $BEKET_API_KEY"
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.

POST /audits/{auditId}/prompts/generate

Generates the prompts for this audit and returns the resulting set, leaving the audit awaiting prompt review. This call costs money — it runs an LLM generation — so treat it as a one-time step per audit rather than something to retry casually.

Both body fields are optional. Sending a non-empty topicIds selects the deterministic template path; omitting it generates over the audit’s selected angles. languages overrides the audit’s stored targeting languages for this generation only.

Requires status to be AWAITING_CONFIG or AWAITING_PROMPTS, and answers 409 otherwise. A newly created audit is PENDING: call POST /audits/{auditId}/prepare first and wait for it to reach AWAITING_CONFIG.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/generate" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"topicIds":[]}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
topicIdsstring[]
languagesstring[]
FieldTypeRequiredDescription
successbooleanyes
dataPromptSetyes

POST /audits/{auditId}/prompts/generate-more

Tops the set back up: each selected angle short of its share of the plan’s prompt limit gets new LLM-generated prompts, skipping texts the audit already has. Existing prompts are kept. This call costs money — it runs an LLM generation.

Requires status to be AWAITING_PROMPTS (after POST /audits/{auditId}/prompts/generate) and an organization plan; answers 409 otherwise, and when every angle is already at its limit. A 400 means the audit has no brand profile or no selected angles to generate from.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/generate-more" \
-H "Authorization: Bearer $BEKET_API_KEY"
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
successbooleanyes
dataPromptSetyes

POST /audits/{auditId}/prompts/import

Adds prompts from a CSV file sent as text (at most 1000 rows and 5 MB). A prompt column is required and a topic column files each row, creating up to 50 new topics; other columns are reported in ignoredColumns. A file from the export re-imports as-is.

Send dryRun: true first: it answers 200 with the same per-row report and writes nothing. A real import answers 201. Rows over the plan’s capacity are added unselected (over_capacity), never refused.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/import" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"content":"<content>"}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
contentstringyes
dryRunboolean
replaceSelectionboolean
FieldTypeRequiredDescription
successbooleanyes
dataPromptImportReportyes
{
"success": true,
"data": {
"dryRun": true,
"counts": {
"added": 1,
"restored": 0,
"over_capacity": 0,
"duplicate": 0,
"invalid": 0
},
"topics": {
"matched": 0,
"created": 1
},
"ignoredColumns": [],
"maxQueries": 25,
"rows": [
{
"row": 1,
"outcome": "added"
}
]
}
}

GET /audits/{auditId}/prompts/manage

One page of prompts, filtered and sorted, with the plan’s capacity. Unlike GET /audits/{auditId}/prompts, archived prompts can be listed too. Pass nextCursor back as cursor for the next page; it is null on the last one.

Terminal window
curl "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/manage?cursor=CURSOR&limit=LIMIT" \
-H "Authorization: Bearer $BEKET_API_KEY"
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
cursorquerynostringOpaque cursor from a previous page’s nextCursor.
limitquerynointegerPage size.
statusqueryno“active” | “archived”Active prompts, or the archived ones.
topicIdquerynostringOnly prompts in this topic; none lists prompts in no topic.
promptTypequeryno“UNBRANDED” | “BRANDED” | “RECALL”Only prompts of this type.
languagequerynostringOnly prompts in this language, as a code or name (en, English); none lists prompts whose language is unknown.
selectedqueryno“true” | “false”Only prompts that are (true) or are not (false) selected to run.
qquerynostringOnly prompts whose text contains this.
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.promptsobject[]yes
data.prompts[].idstringyes
data.prompts[].textstringyes
data.prompts[].promptType“UNBRANDED” | “BRANDED” | “RECALL”yes
data.prompts[].topicIdstring | null
data.prompts[].angleIdstring
data.prompts[].languagestring | null
data.prompts[].regionstring | null
data.prompts[].status“active” | “archived”yes
data.prompts[].selectedbooleanyes
data.prompts[].createdAtstringyes
data.prompts[].createdBystring | nullWho added it; null for a generated prompt.
data.prompts[].minedbooleanyesFound in search results rather than generated or written.
data.nextCursorstring | nullyes
data.capacityPromptCapacityyes
{
"success": true,
"data": {
"prompts": [
{
"id": "a3985077-683f-4df2-9b51-6474baab91e2",
"text": "how do I choose a widget vendor",
"selected": true,
"angleId": "CUSTOM",
"language": null,
"promptType": "UNBRANDED",
"topicId": null,
"region": null,
"status": "active",
"createdAt": "2026-10-26T19:53:04.923Z",
"createdBy": null,
"mined": false
},
{
"id": "0f4d5c46-b98e-4854-af39-2f6c7a32c038",
"text": "best widget software for small teams",
"selected": true,
"angleId": "CUSTOM",
"language": null,
"promptType": "UNBRANDED",
"topicId": null,
"region": null,
"status": "active",
"createdAt": "2026-10-26T19:53:04.923Z",
"createdBy": null,
"mined": false
}
],
"nextCursor": null,
"capacity": {
"used": 2,
"cap": 25,
"left": 23
}
}
}

POST /audits/{auditId}/prompts/preview

Renders the prompts the template path would generate from the profile, competitors and topics in the body — not the audit’s stored ones — so an editor can show them before saving. Deterministic and free: no LLM runs and nothing is written. Every body field is optional.

Terminal window
curl -X POST "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/preview" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"profile":{}}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
profileobject
profile.brandNamestring
profile.brandAliasesstring[]
profile.primaryProductstring | null
profile.offerstring | null
profile.descriptionstring | null
profile.icpstring[]
profile.differentiatorsstring[]
profile.painPointsstring[]
profile.verticalstring | null
profile.categoryLabelstring | nullWhat the business does, e.g. “commercial cleaning”. A label that only ranks (“best”, “top”) is refused.
profile.segmentstring | null
profile.marketScope“local” | “regional” | “national” | “online” | null
profile.citystring | null
profile.serviceRadiusstring | null
profile.anchorsobject | null
profile.verifiedClaimsobject[]
profile.verifiedClaims[].textstringyes
profile.verifiedClaims[].verifiedboolean
profile.neutralDescriptionstring | null
profile.painPromptsobject[]
profile.painPrompts[].textstringyes
profile.painPrompts[].promptENstringyes
profile.painPrompts[].promptFRstring | null
profile.painPrompts[].onboolean
competitorsobject[]
competitors[].namestringyes
competitors[].domainstring | nullThe competitor’s site, like domain.com. Blank or null when it has none; anything else that is not a plausible host is a 400.
competitors[].sizeTier“startup” | “smb” | “mid-market” | “enterprise” | “unknown”
competitors[].classification“direct” | “indirect” | “not-competitor”
competitors[].evidencestring | null
topicIdsstring[]
languagesstring[]
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.promptsobject[]yes
data.prompts[].textstringyes
data.prompts[].brandedbooleanyes
data.prompts[].languagestringyes
data.prompts[].topicIdstringyesThe catalog topic the prompt came from.
data.prompts[].funnelStage“awareness” | “consideration” | “decision”yes
{
"success": true,
"data": {
"prompts": []
}
}

PATCH /audits/{auditId}/prompts/selection

Replaces the selection: the prompts named in selectedIds are selected and every other prompt is not. Ids that are not live prompts of this audit are ignored. On a paid plan the selection has a floor, so a run stays meaningful; going under it is a 400 that names the minimum.

Terminal window
curl -X PATCH "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/selection" \
-H "Authorization: Bearer $BEKET_API_KEY" \
-H "Content-Type: application/json" \
-d '{"selectedIds":[]}'
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
selectedIdsstring[]yes
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.promptsPrompt[]yes
data.maxQueriesinteger | nullyes
{
"success": true,
"data": {
"prompts": [
{
"id": "0f4d5c46-b98e-4854-af39-2f6c7a32c038",
"text": "best widget software for small teams",
"selected": true,
"angleId": "CUSTOM",
"language": null,
"promptType": "UNBRANDED",
"topicId": null,
"region": null,
"querySubject": "OFFERING",
"funnelStage": null,
"angleLabel": "Custom",
"isCustom": true,
"branded": false
},
{
"id": "a3985077-683f-4df2-9b51-6474baab91e2",
"text": "how do I choose a widget vendor",
"selected": true,
"angleId": "CUSTOM",
"language": null,
"promptType": "UNBRANDED",
"topicId": null,
"region": null,
"querySubject": "OFFERING",
"funnelStage": null,
"angleLabel": "Custom",
"isCustom": true,
"branded": false
}
],
"maxQueries": 25
}
}

GET /audits/{auditId}/prompts/summary

Counts by state, type and topic — the cheap read for a status line.

Terminal window
curl "https://api.beket.ai/api/v1/audits/AUDIT_ID/prompts/summary" \
-H "Authorization: Bearer $BEKET_API_KEY"
NameInRequiredTypeDescription
auditIdpathyesstringThe audit’s id.
FieldTypeRequiredDescription
successbooleanyes
dataobjectyes
data.capacityPromptCapacityyes
data.activeintegeryes
data.archivedintegeryes
data.byTypeobjectyesActive prompts by type.
data.byType.UNBRANDEDinteger
data.byType.BRANDEDinteger
data.byType.RECALLinteger
data.topicsintegeryes
data.unassignedintegeryesActive prompts filed under no topic.
data.auditStatusstringyesPrompt writes are refused with 409 while the audit runs.
{
"success": true,
"data": {
"capacity": {
"used": 2,
"cap": 25,
"left": 23
},
"active": 3,
"archived": 0,
"byType": {
"UNBRANDED": 3,
"BRANDED": 0,
"RECALL": 0
},
"topics": 0,
"unassigned": 3,
"auditStatus": "COMPLETED"
}
}
FieldTypeRequiredDescription
idstringyes
textstringyes
selectedbooleanyesWhether the next run asks this prompt.
angleIdstringyes
angleLabelstringyes
querySubjectstring
funnelStagestring | null
isCustombooleanyesWritten by a person rather than generated.
brandedbooleanyesWhether the prompt names the brand.
languagestring | null
promptType“UNBRANDED” | “BRANDED” | “RECALL”yes
topicIdstring | null
regionstring | null
firstPartyobject
firstParty.sourcestringyes
firstParty.termstringyes
minedobject
mined.questionIdstringyes
mined.seedKeywordstring
mined.sourceKindstring
mined.seedSourcestring
mined.firstSeenAtstring
mined.answerDomainsstring[]yes
FieldTypeRequiredDescription
usedintegeryesSelected prompts.
capinteger | nullyesThe plan’s ceiling on selected prompts; null when there is none.
leftinteger | nullyesHow many more may be selected; null when there is no ceiling.
FieldTypeRequiredDescription
dryRunbooleanyes
countsobjectyes
counts.addedintegeryes
counts.restoredintegeryes
counts.over_capacityintegeryes
counts.duplicateintegeryes
counts.invalidintegeryes
topicsobjectyes
topics.matchedintegeryes
topics.createdintegeryes
ignoredColumnsstring[]yes
maxQueriesinteger | nullyes
rowsobject[]yes
rows[].rowintegeryes1-based data row; the header is row 0.
rows[].outcome“added” | “restored” | “over_capacity” | “duplicate” | “invalid”yes
rows[].reason“too_short” | “too_long” | “blank” | “archived_in_file” | “duplicate_in_file” | “topic_limit” | “topic_too_long”
rows[].promptIdstring
rows[].topicSetboolean
FieldTypeRequiredDescription
promptsPrompt[]yes
maxQueriesinteger | nullyes
removed“archived” | “deleted”yes
FieldTypeRequiredDescription
readybooleanyes
statusstringyes
promptsPrompt[]yes
maxQueriesinteger | null