> ## Documentation Index > Fetch the complete documentation index at: https://docs.tidyhire.app/llms.txt > Use this file to discover all available pages before exploring further. # Generate AI Call Script > Generates AI call instructions and structured data extraction plan based on company details, task prompt, questions, and FAQs. This endpoint is **AI-powered**. It generates AI call instructions and a structured data extraction plan based on your company details, task prompt, questions, and FAQs. ## What it returns * **instructions** — AI behavior instructions for the call. These can be passed directly to the [Initiate AI Call](/api-reference/endpoint/call-initiate) endpoint as the `instructions` field. * **extract\_variables** — Structured data fields the AI should extract during the call. These can be passed directly to the [Initiate AI Call](/api-reference/endpoint/call-initiate) endpoint as the `extract_variables` field. ## Example Request ```json theme={null} { "company_name": "Acme Corp", "prompt": "Screen candidates for the Senior Software Engineer position and assess their experience with distributed systems.", "questions": [ "How many years of experience do you have with Node.js?", "Have you worked with microservices architecture?", "Describe a challenging system design problem you have solved." ], "faqs": [ { "question": "What is the salary range?", "answer": "The range is $120k - $180k depending on experience." }, { "question": "Is this remote?", "answer": "Yes, fully remote." }, { "question": "What is the interview process?", "answer": "There will be a technical round followed by a system design discussion." } ] } ``` ## Example Response ```json theme={null} { "success": true, "data": { "instructions": "You are a recruiter for Acme Corp screening candidates for the Senior Software Engineer role. Ask about their experience with distributed systems, Node.js, and microservices architecture. Be professional and friendly. If candidates ask about salary, mention the range is $120k - $180k depending on experience. If they ask about remote work, confirm it is fully remote.", "extract_variables": [ { "label": "Years of Experience", "type": "integer", "description": "How many years of professional experience does the candidate have?", "format_example": "5" }, { "label": "Node.js Experience", "type": "boolean", "description": "Does the candidate have experience with Node.js?", "format_example": "true" }, { "label": "Microservices Experience", "type": "string", "description": "Describe the candidate's experience with microservices architecture.", "format_example": "Built and maintained a microservices-based e-commerce platform" } ] } } ``` ## OpenAPI ````yaml POST /api/public/v1/ai/generate-script openapi: 3.1.0 info: title: Tidyhire API description: Tidyhire Public API for ATS integrations version: 1.0.0 servers: - url: https://api.tidyhire.app description: Production security: - apiKey: [] paths: /api/public/v1/ai/generate-script: post: tags: - AI summary: Generate AI Call Script description: >- Generates AI call instructions and structured data extraction plan based on company details, task prompt, questions, and FAQs. operationId: generateCallScript requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/GenerateCallScriptRequest' responses: '200': description: Success. content: application/json: schema: $ref: '#/components/schemas/GenerateCallScriptSuccessResponse' '400': description: Validation Error. content: application/json: schema: $ref: '#/components/schemas/ValidationErrorResponse' '401': description: Unauthorized. content: application/json: schema: $ref: '#/components/schemas/UnauthorizedResponse' '429': description: Rate limit exceeded. content: application/json: schema: $ref: '#/components/schemas/RateLimitErrorResponse' '500': description: Internal error. content: application/json: schema: $ref: '#/components/schemas/InternalErrorResponse' security: - apiKey: [] components: schemas: GenerateCallScriptRequest: type: object required: - company_name - prompt properties: company_name: type: string minLength: 1 description: Name of the company. example: Acme Corp prompt: type: string minLength: 1 description: >- The main task or goal for the AI call. Describes what the AI should accomplish. example: >- Screen candidates for the Senior Software Engineer position and assess their experience with distributed systems. questions: type: array items: type: string minLength: 1 description: Specific questions the AI should ask during the call. example: - How many years of experience do you have with Node.js? - Have you worked with microservices architecture? faqs: type: array items: type: object required: - question - answer properties: question: type: string minLength: 1 description: The frequently asked question. answer: type: string minLength: 1 description: The answer to the question. description: >- Frequently asked questions and their answers to help the AI respond accurately. example: - question: What is the salary range? answer: The range is $120k - $180k depending on experience. - question: Is this remote? answer: Yes, fully remote. end_call_on_disqualification: type: boolean default: false description: >- If true, the AI will automatically end the call when a candidate is disqualified based on screening criteria. example: false GenerateCallScriptSuccessResponse: type: object properties: success: type: boolean example: true data: type: object properties: instructions: type: string description: Generated AI behavior instructions for the call. example: >- You are a recruiter for Acme Corp screening candidates for the Senior Software Engineer role. Ask about their experience with distributed systems. extract_variables: type: array items: $ref: '#/components/schemas/ExtractVariable' description: Structured data fields the AI should extract during the call. ValidationErrorResponse: type: object properties: success: type: boolean example: false code: type: string example: VALIDATION_ERROR message: type: string example: Request validation failed errors: type: array items: type: object properties: field: type: string example: candidates.0.name message: type: string example: Candidate name must be at least 3 characters UnauthorizedResponse: type: object properties: success: type: boolean example: false message: type: string example: Unauthorized error: type: string example: INVALID_API_KEY RateLimitErrorResponse: type: object properties: success: type: boolean example: false code: type: string example: RATE_LIMIT_EXCEEDED message: type: string example: Too many requests InternalErrorResponse: type: object properties: success: type: boolean example: false code: type: string example: UNKNOWN_ERROR message: type: string example: Something went wrong. ExtractVariable: type: object required: - label - type - description properties: label: type: string description: Human-readable name for the variable. example: Years of Experience type: type: string enum: - string - single_select - boolean - integer - number - array - date - datetime description: Data type of the extracted variable. description: type: string description: What the AI should extract. example: How many years of professional experience does the candidate have? format_example: type: string description: Example of the expected output format. example: 5 years choices: type: array items: type: string description: Allowed values for single_select type. securitySchemes: apiKey: type: apiKey in: header name: x-tidyhire-api-key description: Your Tidyhire API key ````