> ## Documentation Index > Fetch the complete documentation index at: https://docs.pepline.ai/llms.txt > Use this file to discover all available pages before exploring further. # Apply review decisions in one call > Up to 200 decisions, each applied through the same verb the dashboard uses and each leaving a curation receipt with the actor (operator key → operator, org credential → owner) and the reason given. Decisions are independent: the response reports per row what applied and what failed. ## OpenAPI ````yaml https://app.pepline.ai/api/v1/openapi.yaml post /reviews openapi: 3.1.0 info: title: pepline API version: '1' description: | The pepline knowledge ingestion API: push knowledge into your organization's library from your own systems — CMS hooks, sync scripts, Zapier/Make/n8n scenarios — and keep whole websites fresh. One inbound API instead of N connectors; you own the trigger, we own idempotency. servers: - url: https://app.pepline.ai/api/v1 security: - bearerAuth: [] tags: - name: Organization description: The identity behind your key — confirm it works and read your agent slugs. - name: Knowledge sources description: >- Push and sync the knowledge your agents stand on — text, files, pages, whole websites. - name: Knowledge facts description: >- Triage the atomic knowledge your sources yielded — review, edit, archive, tier, per-agent scoping. - name: Knowledge gaps description: >- The questions leads asked that your material could not answer — resolve or dismiss them. - name: Ingestion instructions description: >- "Look for" asks — what the reader should specifically capture on a source, a page, or around a fact. - name: Agents description: List and provision agents, and tune each agent's widget settings. - name: Conversations description: >- Read the conversations your agents have held — transcripts, captured answers, verdicts. - name: Services description: The offerings your agents present and reason about. - name: Fit criteria description: What makes a good or poor lead — the signals your agents qualify against. - name: Voice profiles description: How your agents sound — tone, formality, phrasing. - name: Identities description: >- The personas your agents act as for outward operations — sender name, address, signature. - name: Prompt templates description: >- Versioned prompt bodies per kind — author a new version, activate any prior one. - name: Deliverable templates description: >- The A/B variants of the wrap-up document — sections and guidance per variant. - name: Flow description: >- Author an agent's conversation — its phases and the answers each one captures. - name: Catalog description: >- Draft services, voice, and fit criteria from your knowledge, then accept or dismiss the proposals. - name: Onboarding description: >- Where the organization stands with setup — stage, blockers, what awaits review. paths: /reviews: post: tags: - Onboarding summary: Apply review decisions in one call description: > Up to 200 decisions, each applied through the same verb the dashboard uses and each leaving a curation receipt with the actor (operator key → operator, org credential → owner) and the reason given. Decisions are independent: the response reports per row what applied and what failed. operationId: applyReviews requestBody: required: true content: application/json: schema: type: object required: - decisions properties: decisions: type: array maxItems: 200 items: $ref: '#/components/schemas/ReviewDecision' responses: '200': description: Per-decision outcomes. content: application/json: schema: $ref: '#/components/schemas/ReviewResultList' '401': $ref: '#/components/responses/Unauthorized' '422': $ref: '#/components/responses/Invalid' components: schemas: ReviewDecision: type: object required: - kind - id - action properties: kind: type: string enum: - service - service_proposal - fit_proposal - flow_proposal - voice_proposal - fact - criterion - voice - page id: type: integer description: The row's id; for page, the source id. action: type: string description: >- keep | dismiss | restore | edit | accept | reconsider | apply | read, per kind. reason: type: string description: Why — recorded on the receipt; what the owner reads. fields: type: object description: >- edit: the fields to set; fact dismiss: scope; voice keep: optional name, formality, sign_off_style, tone_rules, languages; page read: urls. additionalProperties: true ReviewResultList: type: object required: - object - data - has_more - applied - failed properties: object: type: string const: list data: type: array items: type: object required: - kind - id - action - status properties: kind: type: string id: type: integer action: type: string status: type: string enum: - ok - error error: type: string receipt_id: type: integer has_more: type: boolean applied: type: integer failed: type: integer Error: type: object required: - error properties: error: type: object required: - type - code - message properties: type: type: string enum: - authentication_error - invalid_request_error - rate_limit_error - api_error code: type: string enum: - missing_api_key - invalid_api_key - resource_missing - method_not_allowed - resource_archived - idempotency_conflict - parameter_invalid - parameter_missing - parameter_unknown - organization_required - organization_paused - rate_limited - flow_invalid - organization_unverified - experiment_running - resource_in_use - not_revertible - credits_exhausted - internal message: type: string param: type: string responses: Unauthorized: description: Missing, malformed, or revoked API key. content: application/json: schema: $ref: '#/components/schemas/Error' Invalid: description: Validation failed — `error.param` names the field. content: application/json: schema: $ref: '#/components/schemas/Error' securitySchemes: bearerAuth: type: http scheme: bearer description: >- Your secret key (pep_sk_…) from Settings → API. Keys are org-scoped; treat them like passwords. ````