> ## Documentation Index > Fetch the complete documentation index at: https://docs.getsales.io/llms.txt > Use this file to discover all available pages before exploring further. # Preview playtable field run > Run an unsaved action_ai_research column against ONE row and answer what its cell would hold: before the column exists, or with the edited prompt of one that does (the drawer's per-row Preview). The same gate, model resolution and output coercion as the paid run, so a preview never promises what the run refuses. PRICED AS ONE ROW: the platform's charge comes back in credits_charged; a row the gate skips (will_run false, skip_reason run_condition_not_met or empty_context) costs nothing. Writes nothing: no cell, no run, no ledger receipt. Every call asks the model again with a fresh key, so a repeat may answer differently and is charged again. Read value, reasoning and confidence; error_code names a refusal before any charge (model_not_in_catalog, web_search_not_supported), a failed call, or an answer that could not be coerced to payload.output (the model ran and was paid). Show the user the sample and its cost; the whole column is create_playtable_run after estimate_playtable_run. Contract: - MCP tool `preview_playtable_field_run`, registry package `mcp.playtables/playtable_fields`, mount `playtables.columns`. - Operation `action`, response envelope `action`. - Flags: none. ## OpenAPI ````yaml /api-reference/playtables/openapi.yaml post /api/playtable-fields/preview-run openapi: 3.0.3 info: title: 'GetSales public contract: gs.service.playtables' description: >- The data platform and the outreach engine: tables of people and companies, their enrichment columns, cells and runs, the data sources that feed them, sender profiles, the stoplist, the activity feed, the credit ledger, and the multichannel workflows with their per-person journeys and tasks. GENERATED. This document is projected from the Zod MCP tool registry in `product/mcp/gs.mcp` (one tool per public endpoint, 1:1). Do not edit it by hand; edit the tool definition and regenerate with `pnpm openapi:public`. Surface: the public `/api` contract of `gs.service.playtables`, 142 operations. This is the only OpenAPI document the platform publishes. Internal (`/internal`) and health endpoints are deliberately absent: they are not part of any contract, they can change without notice, and the service source is their only description. Conventions: - Auth is a bearer JWT, optionally narrowed by the `Team-SID` header. - Every success body is an MCP envelope: `success: true` plus one typed `operation` shape (`search`, `get`, `create`, `update`, `delete`, `metrics`, `group_by`, `action`), and a `meta` block with `trace_id` for support. - Every failure is the same `McpError` envelope with a code from a fixed 16-code taxonomy, so a client maps errors once. - Lists page with `page_size` (0 to 500, default 50) plus an opaque forward `cursor`; `page_size: 0` returns counts only. - On `GET` and `DELETE`, object-valued query parameters (`filter`, `sort`) travel as JSON text and array-valued ones repeat as `name[]=value`. - The MCP-only `_meta` field (usage analytics) never reaches the backend and is not part of this contract. version: '1.0' contact: name: GetSales url: https://getsales.io email: support@getsales.io license: name: Proprietary url: https://getsales.io/terms servers: - url: https://beta.getsales.io/playtables/v1 description: >- Production (the gateway path on the beta ring; the origin is provisioned per DEPLOY_MAP.md) security: - BearerJwt: [] TeamSid: [] tags: - name: activities description: >- Registry package `mcp.playtables/activities`, served on MCP mount `playtables.journeys`. - name: activity_objects description: >- Registry package `mcp.playtables/activity_objects`, served on MCP mount `playtables.people`. - name: companies description: >- Registry package `mcp.playtables/companies`, served on MCP mount `playtables.people`. - name: credit_ledger_entries description: >- Registry package `mcp.playtables/credit_ledger_entries`, served on MCP mount `id.billing`. - name: data_source_items description: >- Registry package `mcp.playtables/data_source_items`, served on MCP mount `playtables.sources`. - name: data_sources description: >- Registry package `mcp.playtables/data_sources`, served on MCP mount `playtables.sources`. - name: notes description: >- Registry package `mcp.playtables/notes`, served on MCP mount `playtables.pipeline`. - name: people description: >- Registry package `mcp.playtables/people`, served on MCP mount `playtables.people`. - name: pipeline_stages description: >- Registry package `mcp.playtables/pipeline_stages`, served on MCP mount `playtables.pipeline`. - name: plays description: >- Registry package `mcp.playtables/plays`, served on MCP mount `playtables.pipeline`. - name: playtable_field_values description: >- Registry package `mcp.playtables/playtable_field_values`, served on MCP mount `playtables.columns`. - name: playtable_fields description: >- Registry package `mcp.playtables/playtable_fields`, served on MCP mount `playtables.columns`. - name: playtable_runs description: >- Registry package `mcp.playtables/playtable_runs`, served on MCP mount `playtables.columns`. - name: playtable_views description: >- Registry package `mcp.playtables/playtable_views`, served on MCP mount `playtables.tables`. - name: playtables description: >- Registry package `mcp.playtables/playtables`, served on MCP mount `playtables.tables`. - name: result_pages description: >- Registry package `mcp.playtables/result_pages`, served on MCP mount `playtables.tables`. - name: sender_profiles description: >- Registry package `mcp.playtables/sender_profiles`, served on MCP mount `playtables.sources`. - name: stoplist_entries description: >- Registry package `mcp.playtables/stoplist_entries`, served on MCP mount `playtables.stoplist`. - name: tags description: >- Registry package `mcp.playtables/tags`, served on MCP mount `playtables.pipeline`. - name: workflow_attachments description: >- Registry package `mcp.playtables/workflow_attachments`, served on MCP mount `playtables.workflows`. - name: workflow_records description: >- Registry package `mcp.playtables/workflow_records`, served on MCP mount `playtables.journeys`. - name: workflow_sources description: >- Registry package `mcp.playtables/workflow_sources`, served on MCP mount `playtables.workflows`. - name: workflow_tasks description: >- Registry package `mcp.playtables/workflow_tasks`, served on MCP mount `playtables.journeys`. - name: workflow_versions description: >- Registry package `mcp.playtables/workflow_versions`, served on MCP mount `playtables.workflows`. - name: workflows description: >- Registry package `mcp.playtables/workflows`, served on MCP mount `playtables.workflows`. paths: /api/playtable-fields/preview-run: post: tags: - playtable_fields summary: Preview playtable field run description: >- Run an unsaved action_ai_research column against ONE row and answer what its cell would hold: before the column exists, or with the edited prompt of one that does (the drawer's per-row Preview). The same gate, model resolution and output coercion as the paid run, so a preview never promises what the run refuses. PRICED AS ONE ROW: the platform's charge comes back in credits_charged; a row the gate skips (will_run false, skip_reason run_condition_not_met or empty_context) costs nothing. Writes nothing: no cell, no run, no ledger receipt. Every call asks the model again with a fresh key, so a repeat may answer differently and is charged again. Read value, reasoning and confidence; error_code names a refusal before any charge (model_not_in_catalog, web_search_not_supported), a failed call, or an answer that could not be coerced to payload.output (the model ran and was paid). Show the user the sample and its cost; the whole column is create_playtable_run after estimate_playtable_run. Contract: - MCP tool `preview_playtable_field_run`, registry package `mcp.playtables/playtable_fields`, mount `playtables.columns`. - Operation `action`, response envelope `action`. - Flags: none. operationId: preview_playtable_field_run requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/PreviewPlaytableFieldRunRequest' responses: '200': description: '`action` success envelope.' content: application/json: schema: $ref: '#/components/schemas/PreviewPlaytableFieldRunResponse' 4XX: $ref: '#/components/responses/McpClientError' 5XX: $ref: '#/components/responses/McpServerError' components: schemas: PreviewPlaytableFieldRunRequest: type: object description: Request body of `preview_playtable_field_run`. properties: playtable_sid: type: string minLength: 18 maxLength: 18 pattern: ^pt_tb_ description: Owner playtable sid (pt_tb_…). object_sid: type: string minLength: 18 maxLength: 18 description: >- The one row to try the draft on (cr_pp_… or cr_co_…), of this table and this team. type: type: string enum: - action_ai_research description: >- What the draft column is. Only action_ai_research runs inline today: waterfall and tool columns run through the queued executor and have no preview. payload: type: object properties: prompt: type: string minLength: 1 maxLength: 8192 description: >- Twig-templated research instruction; the template's variables, an unknown one 422. What the source found on a person (the role, the location) is in the Data source cell: {{record.data_source}} (its slug on a new table) reads it whole. model: type: string minLength: 1 maxLength: 128 description: >- 'auto' (gtm-api routes the call) or a concrete gtm-api model id; validated against the gtm-api registry at save. output: type: string enum: - text - number - select - json description: >- Cell shape: text | number (non-numeric model answer → cell error) | select (one of payload.options) | json (extract values into columns via extraction formulas record..; push onto people/company attributes via output_mapping). options: type: array nullable: true items: type: string minItems: 1 description: Required (min 1) when output=select; null otherwise. output_mapping: type: array nullable: true items: type: object properties: path: type: string minLength: 1 maxLength: 512 description: >- JSON path into the tool/model result, e.g. $.email or $.techs[0].name. target: type: string minLength: 1 maxLength: 128 description: >- Entity-attribute target ONLY: people. or company. (writable-attribute registries; fill-if-empty at projection); validated at save. No record. targets: columns pull via extraction formulas (record..), never via push mapping. required: - path - target maxItems: 20 description: >- Project a 'json' result onto people/company attributes, fill-if-empty (max 20); null = no attribute writes. Columns pull via extraction formulas instead. web_search: type: boolean description: >- Default false: the model answers with the vendor's server-side web search on. A per-model capability: 422 relation_not_found at save, and web_search_not_supported on a preview, for a model without it. required: - prompt - model - output - options - output_mapping description: >- The drawer's live draft (prompt, model, output, options, output_mapping, web_search), validated exactly like create_playtable_field's: a payload that previews is a payload that saves. run_condition: anyOf: - type: object properties: and: type: array items: type: object additionalProperties: {} description: >- Recursive node: the same object shape repeats here. A static OpenAPI document cannot express the cycle, so this level is documented as an open object. minItems: 1 maxItems: 20 required: - and additionalProperties: false - type: object properties: or: type: array items: type: object additionalProperties: {} description: >- Recursive node: the same object shape repeats here. A static OpenAPI document cannot express the cycle, so this level is documented as an open object. minItems: 1 maxItems: 20 required: - or additionalProperties: false - type: object properties: not: type: object additionalProperties: {} description: >- Recursive node: the same object shape repeats here. A static OpenAPI document cannot express the cycle, so this level is documented as an open object. required: - not additionalProperties: false - type: object properties: any: type: object properties: path: type: string minLength: 1 description: >- Array-valued path - the only way to reach inside an array. where: type: object additionalProperties: {} description: >- Recursive node: the same object shape repeats here. A static OpenAPI document cannot express the cycle, so this level is documented as an open object. required: - path - where additionalProperties: false required: - any additionalProperties: false - type: object properties: field: type: string minLength: 1 description: >- Namespaced path: record. or a built-in object attribute; element-relative inside any.where. op: type: object properties: eq: anyOf: - type: string - type: number - type: boolean ne: anyOf: - type: string - type: number - type: boolean in: type: array items: anyOf: - type: string - type: number - type: boolean minItems: 1 maxItems: 100 nin: type: array items: anyOf: - type: string - type: number - type: boolean minItems: 1 maxItems: 100 gt: anyOf: - type: number - type: string gte: anyOf: - type: number - type: string lt: anyOf: - type: number - type: string lte: anyOf: - type: number - type: string is_null: type: boolean contains: type: string minLength: 1 not_contains: type: string minLength: 1 contains_any: type: array items: type: string minLength: 1 minItems: 1 maxItems: 50 not_contains_any: type: array items: type: string minLength: 1 minItems: 1 maxItems: 50 starts_with: type: string minLength: 1 additionalProperties: false required: - field - op additionalProperties: false - {} description: >- The draft gate; a row it skips costs nothing and answers will_run false. null or absent = no gate. required: - playtable_sid - object_sid - type - payload PreviewPlaytableFieldRunResponse: type: object properties: success: type: boolean enum: - true operation: type: string enum: - action action: type: string description: kebab-case verb; matches the route segment. item: {} result: type: object properties: object_sid: type: string will_run: type: boolean description: >- false = the gate or the empty-context rule skipped the row: no call, no charge, skip_reason says which. skip_reason: type: string nullable: true description: >- run_condition_not_met (the gate) or empty_context (every row reference of the prompt resolved to nothing); null when the row ran. value: type: string nullable: true description: >- What the cell would hold; null when the row was skipped, the call failed or the answer could not be coerced to payload.output. error_code: type: string nullable: true description: >- model_not_in_catalog or web_search_not_supported (refused before any charge), a lane code (the call failed), or the coercion failure of an answer the model gave and the team paid for; null on success. error_message: type: string nullable: true reasoning: type: string nullable: true description: The model's reasoning when it gave one. confidence: type: string nullable: true model: type: string nullable: true description: >- The model that answered (the resolved one when payload.model is auto); null when nothing was called. credits_charged: type: number minimum: 0 description: >- The platform's own charge for this one row, in credits; 0 on a skip or a refusal before the call. duration_ms: type: integer minimum: 0 required: - object_sid - will_run - skip_reason - value - error_code - error_message - reasoning - confidence - model - credits_charged - duration_ms meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - operation - action - item - result - meta McpError: type: object properties: success: type: boolean enum: - false error: type: object properties: code: type: string enum: - validation_failed - nothing_to_update - not_found - relation_not_found - invalid_transition - limit_exceeded - payment_required - duplicate_rejected - conflict - delete_blocked - unauthorized - forbidden - rate_limited - internal_error - service_unavailable - not_implemented message: type: string recoverable: type: boolean suggestion: type: string field_errors: type: object additionalProperties: type: array items: type: object properties: rule: type: string message: type: string required: - rule - message blockers: type: array items: type: object properties: type: type: string description: >- Machine-readable blocker type (active_flow, pending_tasks, …). severity: type: string enum: - hard - soft description: >- hard = external action required; soft = acknowledge is enough. description: type: string entity_sid: type: string nullable: true count: type: integer resolution: type: string description: 'Hard: tool name to call. Soft: code for acknowledge[].' resolution_hint: type: string required: - type - severity - description - entity_sid - resolution - resolution_hint context: type: object additionalProperties: {} required: - code - message - recoverable meta: type: object properties: trace_id: type: string description: UUID v7; same 128-bit value as the X-Trace-Id header. span_id: type: string pattern: ^[0-9a-f]{16}$ description: 16 hex chars, root span of this request. timestamp: type: string description: ISO 8601 UTC (Y-m-dTH:i:sZ), response time. duration_ms: type: integer minimum: 0 description: Server-side wall clock. team_sid: type: string nullable: true description: >- The team this call ran in (the token team, or the team_sid override). Null when unauthenticated; absent from pre-2026-08-20 backends. actor_type: type: string nullable: true description: >- user | agent | api_key | system. Null when unauthenticated; absent from pre-2026-08-20 backends. required: - trace_id - span_id - timestamp - duration_ms required: - success - error responses: McpClientError: description: >- MCP error envelope. `error.code` is one of validation_failed, nothing_to_update, not_found, relation_not_found, invalid_transition, limit_exceeded, payment_required, duplicate_rejected, conflict, delete_blocked, unauthorized, forbidden, rate_limited, not_implemented. content: application/json: schema: $ref: '#/components/schemas/McpError' McpServerError: description: >- MCP error envelope with `error.code` internal_error or service_unavailable. content: application/json: schema: $ref: '#/components/schemas/McpError' securitySchemes: BearerJwt: type: http scheme: bearer bearerFormat: JWT description: >- Access token issued by gs.service.id. Its `access_identity` claim carries `team_sid`, `actor_sid` and `actor_type`, and that team scope is authoritative. TeamSid: type: apiKey in: header name: Team-SID description: >- Team scope for tokens that do not carry one. Ignored when the token already names a team. ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.