> ## Documentation Index > Fetch the complete documentation index at: https://docs.sagescreen.dev/llms.txt > Use this file to discover all available pages before exploring further. # Generate AI analysis for a context > Loads the context from Redis, sends the job description, role, and role level to the AI model, and returns enriched context data including: - **summary** -- AI-generated summary of the role - **categories** -- Structured evaluation categories - **category_titles** -- Comma-separated list of category names - **metrics** -- Assessment metrics for the role The generated data is also saved to the Prompt Library (PL) service. ## OpenAPI ````yaml /openapi/private/specs/services/context.yml get /context/{context_id}/generate openapi: 3.1.0 info: title: Context Service API description: > Manages context data for council sages. Context represents the job description, role, and AI-generated analysis (summary, categories, metrics) used during screening interviews. ## Authentication All endpoints require authentication via one of two methods: - **API Key**: Pass the key in the `X-Auth` header (service-to-service calls) - **JWT Token**: Pass a Bearer token in the `Authorization` header (user-facing calls) The required permission level is noted per endpoint. ## Context Lifecycle 1. **Create** -- Context is created with job description, role, and role level 2. **Store** -- Context is saved to Redis for fast retrieval during screening 3. **Generate** -- AI analyzes the context to produce summary, categories, and metrics 4. **Save** -- Generated data is persisted to the Prompt Library (PL) service ## Business Rules - Context is stored in Redis for low-latency access during interviews - `context_id` must be provided and valid for all read operations - The generate endpoint calls AI to produce structured analysis from the job context - Update and Delete endpoints are not yet implemented (return 501) version: 1.0.0 contact: name: Platform Team servers: - url: '{protocol}://{host}:{port}' description: Context Service variables: protocol: default: https enum: - http - https host: default: localhost port: default: '5000' security: [] tags: - name: Context description: Context CRUD and AI generation - name: Service description: Health checks and initialization paths: /context/{context_id}/generate: get: tags: - Context summary: Generate AI analysis for a context description: > Loads the context from Redis, sends the job description, role, and role level to the AI model, and returns enriched context data including: - **summary** -- AI-generated summary of the role - **categories** -- Structured evaluation categories - **category_titles** -- Comma-separated list of category names - **metrics** -- Assessment metrics for the role The generated data is also saved to the Prompt Library (PL) service. operationId: generateContext parameters: - $ref: '#/components/parameters/ContextId' - $ref: '#/components/parameters/RequiredPermission_council_sage' responses: '200': description: Context generated and saved successfully content: application/json: schema: $ref: '#/components/schemas/ContextGenerateResponse' example: id: a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d name: Senior Software Engineer context: >- We are looking for a senior software engineer with 5+ years of experience in Python and cloud infrastructure... role: Software Engineer role_level: senior council_sage_id: c3d4e5f6-7890-4abc-def0-123456789abc summary: >- This role requires a seasoned engineer with deep expertise in Python, AWS, and distributed systems... categories: technical_skills: title: Technical Skills description: Python, cloud infrastructure, distributed systems problem_solving: title: Problem Solving description: System design, debugging, optimization category_titles: >- "Technical Skills", "Problem Solving", "Communication", "Leadership", "Architecture" metrics: complexity: high seniority_match: senior '400': description: Missing context ID content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error: context_id must be set before generating '401': $ref: '#/components/responses/Unauthorized' '404': description: Context not found in Redis content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' example: error: Context with ID a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d not found '500': description: AI generation or save error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: systemPromptMissing: summary: System prompt not configured value: error: system_prompt must be set before generating aiError: summary: AI generation failed value: error: >- Error generating context data: APIError('Model unavailable') saveError: summary: Error saving to PL value: error: >- Error saving context to PL: ConnectionError('Connection refused') security: - jwtAuth: [] components: parameters: ContextId: name: context_id in: path required: true description: UUID of the context record schema: type: string format: uuid example: a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d RequiredPermission_council_sage: name: X-Permission-Info in: header required: false description: >- **Required JWT permission: `council_sage`** (informational only -- enforced server-side) schema: type: string schemas: ContextGenerateResponse: type: object description: Context enriched with AI-generated analysis properties: id: type: string format: uuid name: type: string context: type: string role: type: string role_level: type: string council_sage_id: type: string format: uuid summary: type: string description: AI-generated summary of the role requirements categories: type: object additionalProperties: true description: Structured evaluation categories produced by AI category_titles: type: string description: Comma-separated quoted category names metrics: type: object additionalProperties: true description: Assessment metrics for the role ErrorResponse: type: object required: - error properties: error: type: string description: Human-readable error message responses: Unauthorized: description: Authentication failed content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: noApiKey: summary: Missing API key value: error: Unauthorized - API key required invalidApiKey: summary: Invalid API key value: error: Unauthorized - Invalid API key noToken: summary: Missing JWT token value: error: Unauthorized - No valid token invalidToken: summary: Invalid or expired JWT value: error: Unauthorized3 insufficientPermissions: summary: Token lacks required permission value: error: Unauthorized4 securitySchemes: jwtAuth: type: http scheme: bearer bearerFormat: JWT description: User JWT token passed in Authorization header ````