> ## Documentation Index > Fetch the complete documentation index at: https://docs.api.tamtam.ai/llms.txt > Use this file to discover all available pages before exploring further. # Start a lead generation run > Sweep several of the signals you already have, all at once, and collect what they find into one list, up to `target_leads`. This is what makes a signal run at all: a signal no program picks never sweeps. It records a lead generation program with no schedule (open it under Settings > Signals > Lead generation to put it on one, add a lead score floor or firmographic rules, rewrite the QA prompt or choose the lists it fills) and starts a run of it immediately. It creates no signal. Pick the signals from [List signals](/api-reference/signals/list-signals). Every kind with a sweep of its own can be picked; the inbox signals and job change alerts cannot. With `qa_enabled` the run collects about 30% more than the target and has an AI judge each lead against your ICP and personas, dropping the ones that fail. **This is the operation that spends.** Starting a run starts every picked signal's own sweep immediately, each billing at its own rate (per post or article judged, per person collected), and the QA adds one AI call per lead judged. A run can take from minutes to hours; this returns as soon as it has started. ## OpenAPI ````yaml /reference/openapi.yaml post /v2/lead-generation-runs openapi: 3.1.0 info: title: Tamtam Public API version: 2.0.0 servers: - url: https://api.tamtam.ai/api security: [] paths: /v2/lead-generation-runs: post: tags: - Signals summary: Start a lead generation run description: >- Sweep several of the signals you already have, all at once, and collect what they find into one list, up to `target_leads`. This is what makes a signal run at all: a signal no program picks never sweeps. It records a lead generation program with no schedule (open it under Settings > Signals > Lead generation to put it on one, add a lead score floor or firmographic rules, rewrite the QA prompt or choose the lists it fills) and starts a run of it immediately. It creates no signal. Pick the signals from [List signals](/api-reference/signals/list-signals). Every kind with a sweep of its own can be picked; the inbox signals and job change alerts cannot. With `qa_enabled` the run collects about 30% more than the target and has an AI judge each lead against your ICP and personas, dropping the ones that fail. **This is the operation that spends.** Starting a run starts every picked signal's own sweep immediately, each billing at its own rate (per post or article judged, per person collected), and the QA adds one AI call per lead judged. A run can take from minutes to hours; this returns as soon as it has started. operationId: start-lead-generation-run parameters: - description: >- Target account UUID. Required for staff callers; ignored for customer API keys. explode: false in: query name: account_id schema: description: >- Target account UUID. Required for staff callers; ignored for customer API keys. type: string requestBody: content: application/json: schema: $ref: '#/components/schemas/StartLeadGenerationRunBody' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/LeadGenerationRunStartedDto' description: OK default: content: application/problem+json: schema: $ref: '#/components/schemas/ErrorModel' description: Error security: - apikeyAuth: [] - bearerAuth: [] components: schemas: StartLeadGenerationRunBody: additionalProperties: false properties: name: description: >- Optional name for the program, which also names the list its runs fill. Omit for a timestamped default. maxLength: 120 type: string qa_enabled: description: >- Have an AI judge each lead against your ICP and personas and drop the failures. Defaults to true. type: boolean signals: description: >- One to twenty signals to sweep, from List signals. Every kind with a sweep of its own can be picked. items: $ref: '#/components/schemas/LeadGenerationSignalPickDto' maxItems: 20 minItems: 1 type: - array - 'null' target_leads: description: How many leads you want in the list. format: int64 maximum: 2000 minimum: 1 type: integer required: - target_leads - signals type: object LeadGenerationRunStartedDto: additionalProperties: false properties: name: type: string program_id: description: >- The program recorded for this run, with no schedule. Open it under Settings > Signals > Lead generation to put it on one. type: string qa_enabled: type: boolean run_id: type: string signals: description: How many signals the run sweeps. format: int64 type: integer target_leads: format: int32 type: integer required: - program_id - run_id - name - target_leads - qa_enabled - signals type: object ErrorModel: additionalProperties: false properties: detail: description: >- A human-readable explanation specific to this occurrence of the problem. examples: - Property foo is required but is missing. type: string errors: description: Optional list of individual error details items: $ref: '#/components/schemas/ErrorDetail' type: - array - 'null' instance: description: >- A URI reference that identifies the specific occurrence of the problem. examples: - https://example.com/error-log/abc123 format: uri type: string status: description: HTTP status code examples: - 400 format: int64 type: integer title: description: >- A short, human-readable summary of the problem type. This value should not change between occurrences of the error. examples: - Bad Request type: string type: default: about:blank description: A URI reference to human-readable documentation for the error. examples: - https://example.com/errors/example format: uri type: string type: object LeadGenerationSignalPickDto: additionalProperties: false properties: id: description: The signal's id from List signals. type: string kind: description: The signal's kind, exactly as List signals reports it. enum: - linkedin_content - news_content - job_posting - page_follower - new_hire - past_company_move - deal_stage_lookalike - agent type: string required: - kind - id type: object ErrorDetail: additionalProperties: false properties: location: description: >- Where the error occurred, e.g. 'body.items[3].tags' or 'path.thing-id' type: string message: description: Error message text type: string value: description: The value at the given location type: object securitySchemes: apikeyAuth: description: Account API key passed in the Authorization header in: header name: Authorization type: apiKey bearerAuth: description: Bearer JWT obtained via the OAuth 2.1 authorization flow scheme: bearer type: http ````