> ## Documentation Index > Fetch the complete documentation index at: https://docs.nx1cloud.com/llms.txt > Use this file to discover all available pages before exploring further. # Get a feature engineering proposal > Return the latest proposal for a job, including the recipe, SQL, and validation summary. ## OpenAPI ````yaml get /api/automl/feature-engineering/jobs/{job_id} openapi: 3.1.0 info: title: Nx1 AI API description: | AI API for Nx1 Data Platform Management and Automated Data Tasks. Authentication is required via PSK in Authorization header. Default PSK is | [ask a friend] | version: 0.10.2 servers: [] security: [] paths: /api/automl/feature-engineering/jobs/{job_id}: get: tags: - AutoML Feature Engineering summary: Get a feature engineering proposal description: >- Return the latest proposal for a job, including the recipe, SQL, and validation summary. operationId: get_job_api_automl_feature_engineering_jobs__job_id__get parameters: - name: job_id in: path required: true schema: type: string format: uuid description: Feature engineering job ID. title: Job Id description: Feature engineering job ID. responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/AutoMLFeatureEngineeringProposal' '404': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' description: Not Found '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' security: - OAuth2AuthorizationCodeBearer: [] - APIKeyHeader: [] components: schemas: AutoMLFeatureEngineeringProposal: properties: job_id: type: string format: uuid title: Job Id status: $ref: '#/components/schemas/AutoMLFeatureEngineeringStatusEnum' target_table_name: type: string title: Target Table Name domain: type: string title: Domain owner: type: string title: Owner recipe: anyOf: - $ref: '#/components/schemas/FeatureRecipe' - type: 'null' sql: anyOf: - type: string - type: 'null' title: Sql description: The `CREATE TABLE AS SELECT` query the crew produced. validation: anyOf: - $ref: '#/components/schemas/ValidationSummary' - type: 'null' error: anyOf: - type: string - type: 'null' title: Error created_at: type: string format: date-time title: Created At updated_at: type: string format: date-time title: Updated At type: object required: - job_id - status - target_table_name - domain - owner - created_at - updated_at title: AutoMLFeatureEngineeringProposal description: The crew's proposal returned to the user for review. ErrorResponse: properties: error: type: string title: Error description: A brief description of the error that occurred. code: type: integer title: Code description: The HTTP status code associated with the error. default: 500 type: object required: - error title: ErrorResponse HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError AutoMLFeatureEngineeringStatusEnum: type: string enum: - running - pending_approval - failed - approved - materializing - complete title: AutoMLFeatureEngineeringStatusEnum description: Lifecycle of an AutoML feature engineering job. FeatureRecipe: properties: target_table: type: string title: Target Table entity_grain: items: type: string type: array title: Entity Grain label: $ref: '#/components/schemas/LabelSpec' features: items: $ref: '#/components/schemas/FeatureDefinition' type: array title: Features notes: anyOf: - type: string - type: 'null' title: Notes description: >- Crew notes on assumptions, leakage risks, or open questions for the reviewer. type: object required: - target_table - entity_grain - label - features title: FeatureRecipe description: Structured recipe describing the training table the crew designed. ValidationSummary: properties: estimated_row_count: anyOf: - type: integer - type: 'null' title: Estimated Row Count description: >- Row count the validation query returned. When equal to the query limit, the actual table has more rows. label_distribution: anyOf: - additionalProperties: type: integer type: object - type: 'null' title: Label Distribution description: Counts per label class observed in the validation sample. high_null_columns: anyOf: - additionalProperties: type: number type: object - type: 'null' title: High Null Columns description: >- Null fraction for output columns where the rate exceeds 5%. Replaces the per-column null_rates dict to keep the JSON small. warnings: anyOf: - items: type: string type: array - type: 'null' title: Warnings description: >- Validation warnings. For example, severe class imbalance or leakage risk. type: object title: ValidationSummary description: |- Result of running the CTAS query with a row limit during validation. Kept intentionally lean. Large agents produce more than 10 KB of JSON when this grows with per-column null rates and sample rows. That often exceeds output-token limits. Run the SQL directly to inspect rows. Only persist what's cheap and structurally useful. ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type input: title: Input ctx: type: object title: Context type: object required: - loc - msg - type title: ValidationError LabelSpec: properties: name: type: string title: Name description: Output column name in the training table. default: label type: type: string const: binary title: Type description: Label type. Version 1 supports binary labels only. default: binary column: anyOf: - type: string - type: 'null' title: Column description: >- Existing column name or a simple SQL expression that yields the label. derivation: anyOf: - type: string - type: 'null' title: Derivation description: >- Natural-language description of how to derive the label from source data. positive_class_value: anyOf: - {} - type: 'null' title: Positive Class Value description: Value treated as the positive class for binary labels. type: object title: LabelSpec description: |- How to derive the label column for the training table. Provide exactly one of ``column`` or ``derivation``. ``column`` refers to an existing column or a simple SQL expression over source columns. ``derivation`` is a natural-language description that the crew translates into SQL. FeatureDefinition: properties: name: type: string title: Name description: Output column name in the training table. expression: type: string title: Expression description: SQL expression producing the feature. source_table: anyOf: - type: string - type: 'null' title: Source Table description: Fully qualified primary source table the feature derives from. description: anyOf: - type: string - type: 'null' title: Description description: Why this feature is useful for the prediction problem. data_type: anyOf: - type: string - type: 'null' title: Data Type description: Inferred Trino data type. For example, `double` or `varchar`. type: object required: - name - expression title: FeatureDefinition description: A single engineered feature in the recipe. securitySchemes: OAuth2AuthorizationCodeBearer: type: oauth2 flows: authorizationCode: scopes: {} authorizationUrl: >- https://sso-rapid.rapid.nx1cloud.com/realms/rapid/protocol/openid-connect/auth tokenUrl: >- https://sso-rapid.rapid.nx1cloud.com/realms/rapid/protocol/openid-connect/token APIKeyHeader: type: apiKey in: header name: Authorization-PSK ````