> ## Documentation Index > Fetch the complete documentation index at: https://docs.interchange.io/llms.txt > Use this file to discover all available pages before exploring further. # List storefront intelligence-run records > Paginated list of intelligence-run records for the storefront, newest first. Each row captures the prompt, raw + parsed LLM output, matched buyer-instructions, and the result envelope. Page with `?skip=` and `?take=`. Filter the seller demand inbox with `?disposition=` (`responded` / `declined_fit` / `declined_policy` / `not_live`); an invalid value returns 400. ## OpenAPI ````yaml /v2/storefront-api-v2.yaml get /intelligence-runs openapi: 3.0.0 info: title: Scope3 Storefront API version: 2.0.0 description: |- REST API for partners to manage storefronts, inventory sources, and billing. ## Authentication All endpoints require a Bearer token in the Authorization header: ``` Authorization: Bearer your-api-key ``` ## Base URL `https://api.interchange.io/api/v2/storefront` ## For AI Agents AI agents can use the MCP endpoint at `/mcp/v2/storefront` with three tools: - `initialize`: Start an MCP session - `api_call`: Make REST API calls - `ask_about_capability`: Learn about API features servers: - url: https://api.interchange.io/api/v2/storefront description: Production server security: [] tags: - name: Account description: Account management, service tokens, and preferences - name: Storefront description: Manage storefront and inventory sources - name: Storefront Agents description: List and manage registered sales, signals, and outcomes agents - name: Storefront Activity description: Audit log of configuration and inventory changes on the storefront - name: Storefront Billing description: Payout bank details and billing configuration for storefronts - name: AI Usage description: Storefront AI token usage visibility by model - name: MCP description: Model Context Protocol endpoints paths: /intelligence-runs: get: tags: - Storefront summary: List storefront intelligence-run records description: >- Paginated list of intelligence-run records for the storefront, newest first. Each row captures the prompt, raw + parsed LLM output, matched buyer-instructions, and the result envelope. Page with `?skip=` and `?take=`. Filter the seller demand inbox with `?disposition=` (`responded` / `declined_fit` / `declined_policy` / `not_live`); an invalid value returns 400. operationId: listIntelligenceRuns parameters: - in: query name: skip schema: description: Number of rows to skip (offset pagination). example: 0 default: 0 type: integer minimum: 0 maximum: 9007199254740991 description: Number of rows to skip (offset pagination). - in: query name: take schema: description: Number of rows to return per page (1–100). example: 25 default: 25 type: integer minimum: 1 maximum: 100 description: Number of rows to return per page (1–100). - in: query name: disposition schema: description: >- Demand-inbox filter — return only runs with this brief outcome: `responded` (the storefront composed a response), `declined_fit` (declined: no matching inventory), `declined_policy` (declined: acceptance-policy violation), or `not_live` (brief arrived before the storefront was live; reserved, not yet emitted). Omit to return every outcome. example: declined_fit type: string enum: - responded - declined_fit - declined_policy - not_live description: >- Demand-inbox filter — return only runs with this brief outcome: `responded` (the storefront composed a response), `declined_fit` (declined: no matching inventory), `declined_policy` (declined: acceptance-policy violation), or `not_live` (brief arrived before the storefront was live; reserved, not yet emitted). Omit to return every outcome. - in: query name: q schema: description: >- Case-insensitive substring search over the buyer brief text. Use to find every brief mentioning a vertical, advertiser, or term (e.g. `fintech`). Combines with `disposition`. example: fintech type: string minLength: 1 maxLength: 200 description: >- Case-insensitive substring search over the buyer brief text. Use to find every brief mentioning a vertical, advertiser, or term (e.g. `fintech`). Combines with `disposition`. - in: query name: buyingMode schema: description: >- Filter by buying mode — `brief` for the demand inbox (excludes wholesale/refine runs), `wholesale`, or `refine`. Omit to return every mode. example: brief type: string enum: - brief - wholesale - refine description: >- Filter by buying mode — `brief` for the demand inbox (excludes wholesale/refine runs), `wholesale`, or `refine`. Omit to return every mode. - in: query name: commercialResult schema: description: >- Filter by the commercial result that followed the storefront response, derived from the latest attributed commercial-outcome event: `booked` (the media buy was forwarded upstream or has reported delivery — a confirmed commitment), `pending` (the media buy is awaiting the operator’s own acceptance-policy approval and could still be rejected), or `rejected` (the storefront rejected the media buy). Runs with no attributed media buy yet match no value. There is no `lost` value — a buyer silently passing on a response has no signal in AdCP today. example: booked type: string enum: - booked - pending - rejected description: >- Filter by the commercial result that followed the storefront response, derived from the latest attributed commercial-outcome event: `booked` (the media buy was forwarded upstream or has reported delivery — a confirmed commitment), `pending` (the media buy is awaiting the operator’s own acceptance-policy approval and could still be rejected), or `rejected` (the storefront rejected the media buy). Runs with no attributed media buy yet match no value. There is no `lost` value — a buyer silently passing on a response has no signal in AdCP today. - in: query name: view schema: description: >- `full` (default) returns every run field. `summary` omits the heavy LLM payload columns (prompt, raw/inventory snapshots) the demand inbox does not render, keeping the response small. The full row is always available on `GET /intelligence-runs/:id`. example: summary default: full type: string enum: - summary - full description: >- `full` (default) returns every run field. `summary` omits the heavy LLM payload columns (prompt, raw/inventory snapshots) the demand inbox does not render, keeping the response small. The full row is always available on `GET /intelligence-runs/:id`. responses: '200': description: List storefront intelligence-run records content: application/json: schema: $ref: '#/components/schemas/IntelligenceRunListResponse' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - bearerAuth: [] components: schemas: IntelligenceRunListResponse: description: List of intelligence runs for a storefront. type: object properties: items: type: array items: $ref: '#/components/schemas/IntelligenceRunResponse' total: type: integer minimum: 0 maximum: 9007199254740991 required: - items - total additionalProperties: false ErrorResponse: description: Standard error response type: object properties: data: type: string nullable: true enum: - null error: $ref: '#/components/schemas/ApiError' required: - data - error additionalProperties: false IntelligenceRunResponse: description: >- A single storefront intelligence run: inputs, prompt, raw + parsed LLM output, persisted product ids, and result envelope. type: object properties: id: type: string storefrontId: type: string buyerCustomerId: nullable: true type: integer minimum: -9007199254740991 maximum: 9007199254740991 operatingInstructionsVersion: type: integer minimum: -9007199254740991 maximum: 9007199254740991 buyerScope: $ref: '#/components/schemas/IntelligenceRunBuyerScope' buyerInstructions: $ref: '#/components/schemas/IntelligenceRunBuyerInstructions' brief: nullable: true type: string buyingMode: type: string inventorySnapshot: {} prompt: type: string rawLlmOutput: {} parsedOutput: {} runRationale: nullable: true type: string explanation: $ref: '#/components/schemas/IntelligenceRunExplanation' composedProductIds: type: array items: type: string result: $ref: '#/components/schemas/IntelligenceRunResult' modelProvider: nullable: true type: string modelName: type: string durationMs: nullable: true type: integer minimum: -9007199254740991 maximum: 9007199254740991 refineSnapshot: {} refinementAppliedSnapshot: {} requestAsks: type: array items: type: string shownProductsSnapshot: {} pricingSummary: {} negotiationSummary: $ref: '#/components/schemas/IntelligenceRunNegotiationAnalytics' commercialOutcome: {} evalLabel: {} createdAt: type: string format: date-time pattern: >- ^(?:(?:\d\d[2468][048]|\d\d[13579][26]|\d\d0[48]|[02468][048]00|[13579][26]00)-02-29|\d{4}-(?:(?:0[13578]|1[02])-(?:0[1-9]|[12]\d|3[01])|(?:0[469]|11)-(?:0[1-9]|[12]\d|30)|(?:02)-(?:0[1-9]|1\d|2[0-8])))T(?:(?:[01]\d|2[0-3]):[0-5]\d(?::[0-5]\d(?:\.\d+)?)?(?:Z))$ required: - id - storefrontId - buyerCustomerId - operatingInstructionsVersion - buyerScope - buyerInstructions - brief - buyingMode - inventorySnapshot - prompt - rawLlmOutput - parsedOutput - runRationale - explanation - composedProductIds - result - modelProvider - modelName - durationMs - refineSnapshot - refinementAppliedSnapshot - requestAsks - shownProductsSnapshot - pricingSummary - negotiationSummary - commercialOutcome - evalLabel - createdAt additionalProperties: false ApiError: description: Structured error object type: object properties: code: description: Machine-readable error code type: string message: description: Human-readable error message type: string field: description: Field path associated with the error type: string details: description: Additional error context type: object additionalProperties: {} required: - code - message additionalProperties: false IntelligenceRunBuyerScope: description: >- Buyer scope extracted from the AdCP get_products request that drove this run. type: object properties: operatorDomain: nullable: true type: string brandDomain: nullable: true type: string country: nullable: true type: string required: - operatorDomain - brandDomain - country additionalProperties: false IntelligenceRunBuyerInstructions: description: >- Resolver output: which buyer-instructions rows matched and the effective discount + notes applied. type: object properties: matchedRowIds: type: array items: type: string effectiveDiscountPercent: nullable: true type: number notes: type: array items: type: string required: - matchedRowIds - effectiveDiscountPercent - notes additionalProperties: false IntelligenceRunExplanation: description: >- Sanitized, user-facing explanation derived from the persisted run record: selected products, reasoning, pricing notes, buyer-instruction effects, and failures. type: object properties: summary: type: string selectedProducts: type: array items: $ref: '#/components/schemas/IntelligenceRunProductExplanation' unpricedProducts: type: array items: $ref: '#/components/schemas/IntelligenceRunUnpricedProductExplanation' buyerInstructionNotes: type: array items: type: string pricingNotes: type: array items: type: string failure: nullable: true type: object properties: code: nullable: true type: string message: nullable: true type: string required: - code - message additionalProperties: false required: - summary - selectedProducts - unpricedProducts - buyerInstructionNotes - pricingNotes - failure additionalProperties: false IntelligenceRunResult: description: >- Outcome envelope: ok on success, error with code/message on failure, skipped when the pipeline short-circuited. type: object properties: kind: type: string enum: - ok - error - skipped code: nullable: true type: string message: nullable: true type: string required: - kind - code - message additionalProperties: false IntelligenceRunNegotiationAnalytics: description: >- Compact seller-facing analytics derived from the buyer request and storefront response: refine counts, ask categories, product ids shown, and acknowledgement counts. IntelligenceRunProductExplanation: description: >- Buyer-safe explanation of one product selected for the storefront response. type: object properties: productId: nullable: true type: string name: nullable: true type: string description: nullable: true type: string reasoning: nullable: true type: string pricing: nullable: true allOf: - $ref: '#/components/schemas/IntelligenceRunProductPricingExplanation' bundleIds: type: array items: type: string signalIds: type: array items: type: string formatIds: type: array items: $ref: '#/components/schemas/IntelligenceRunProductFormatExplanation' required: - productId - name - description - reasoning - pricing - bundleIds - signalIds - formatIds additionalProperties: false IntelligenceRunUnpricedProductExplanation: description: >- Composition the model considered but the platform omitted because it could not be priced authoritatively. type: object properties: name: nullable: true type: string reasoning: nullable: true type: string reason: type: string bundleIds: type: array items: type: string signalIds: type: array items: type: string required: - name - reasoning - reason - bundleIds - signalIds additionalProperties: false IntelligenceRunProductPricingExplanation: description: Server-computed CPM pricing summary for a selected composition. type: object properties: baseCpm: nullable: true type: number currency: nullable: true type: string operatorDiscount: nullable: true type: number finalCpm: nullable: true type: number required: - baseCpm - currency - operatorDiscount - finalCpm additionalProperties: false IntelligenceRunProductFormatExplanation: description: Creative format selected for an explained product. type: object properties: agentUrl: nullable: true type: string id: nullable: true type: string required: - agentUrl - id additionalProperties: false securitySchemes: bearerAuth: type: http scheme: bearer description: API key or access token ````