{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "features": {
    "core": [
      {
        "id": "parallel-export",
        "name": "Parallel Data Export",
        "category": "Performance",
        "description": "Advanced parallel processing engine that splits data extraction across multiple threads, achieving up to 30× performance improvement over sequential tools.",
        "benefits": [
          "Drastically reduced export times",
          "Full bandwidth utilization",
          "Configurable parallelism level",
          "Automatic workload distribution"
        ],
        "technicalDetails": {
          "implementation": "Multi-threaded architecture with smart data partitioning",
          "configuration": "2-3 parameters to enable",
          "maxThreads": "Configurable based on system resources"
        },
        "icon": "Zap"
      },
      {
        "id": "single-executable",
        "name": "Single Executable Deployment",
        "category": "Simplicity",
        "description": "Zero-dependency installation with all database drivers embedded in a single executable file. No MSI, no RPM, no complex setup.",
        "benefits": [
          "Install in under 60 seconds",
          "No dependency conflicts",
          "Portable across environments",
          "Simplified deployment pipeline"
        ],
        "technicalDetails": {
          "format": "Single binary executable",
          "size": "Optimized footprint",
          "embeddedDrivers": ["Oracle", "SQL Server", "PostgreSQL", "MySQL", "ClickHouse", "Teradata", "SAP HANA", "Netezza", "DuckDB"]
        },
        "icon": "Terminal"
      },
      {
        "id": "low-memory",
        "name": "Streaming Architecture",
        "category": "Performance",
        "description": "Memory-efficient streaming design that handles massive datasets (hundreds of gigabytes) with minimal RAM usage.",
        "benefits": [
          "Stable performance on large datasets",
          "No OOM errors",
          "Predictable resource usage",
          "Suitable for constrained environments"
        ],
        "technicalDetails": {
          "architecture": "Stream-based processing",
          "memoryProfile": "Low and constant",
          "maxDatasetSize": "Unlimited (tested with 100GB+ tables)"
        },
        "icon": "MemoryStick"
      },
      {
        "id": "enterprise-logging",
        "name": "Enterprise-Grade Logging",
        "category": "Operations",
        "description": "Comprehensive logging system with multiple sinks including console, JSON files, PostgreSQL, and SQL Server databases.",
        "benefits": [
          "Full audit trail for compliance",
          "Structured JSON logs",
          "Database-backed logging for analytics",
          "Configurable log levels"
        ],
        "technicalDetails": {
          "sinks": ["Console", "JSON Files", "PostgreSQL", "MS SQL Server"],
          "logFormats": ["Structured JSON", "Plain text"],
          "features": ["Variable-based file naming", "Log rotation", "Custom log levels"]
        },
        "icon": "FileText"
      },
      {
        "id": "security",
        "name": "Enterprise Security",
        "category": "Security",
        "description": "Digitally signed executable with CA certification, password obfuscation in logs, and SQL injection prevention.",
        "benefits": [
          "Guaranteed malware-free",
          "Protected credentials in logs",
          "SQL injection attack prevention",
          "Compliance-ready security"
        ],
        "technicalDetails": {
          "signing": "CA-certified digital signature",
          "passwordHandling": "Automatic obfuscation in all log outputs",
          "sqlSecurity": "Built-in parser blocks injection attacks"
        },
        "icon": "Shield"
      },
      {
        "id": "format-support",
        "name": "Multiple Output Formats",
        "category": "Flexibility",
        "description": "Export data to CSV, Parquet, JSON, XLSX, and BSON formats with automatic schema inference.",
        "benefits": [
          "Choose optimal format for use case",
          "Native Parquet support for analytics",
          "JSON for APIs and document stores",
          "Excel compatibility for business users"
        ],
        "supportedFormats": [
          {
            "id": "csv",
            "name": "CSV",
            "extension": ".csv",
            "useCases": ["Data interchange", "Excel import", "Legacy systems"]
          },
          {
            "id": "parquet",
            "name": "Apache Parquet",
            "extension": ".parquet",
            "useCases": ["Data lakes", "Analytics", "Big data platforms", "Columnar storage"]
          },
          {
            "id": "json",
            "name": "JSON",
            "extension": ".json",
            "useCases": ["APIs", "NoSQL databases", "Document stores", "Web applications"]
          },
          {
            "id": "xlsx",
            "name": "Excel",
            "extension": ".xlsx",
            "useCases": ["Business reporting", "Data analysis", "Manual review"]
          },
          {
            "id": "bson",
            "name": "BSON",
            "extension": ".bson",
            "useCases": ["MongoDB", "Binary JSON applications"]
          }
        ],
        "icon": "FileJson"
      },
      {
        "id": "cloud-integration",
        "name": "Cloud Storage Native Support",
        "category": "Cloud",
        "description": "Direct export to AWS S3, Azure Blob Storage, Azure Data Lake, Google Cloud Storage, and Microsoft OneLake without intermediate local storage.",
        "benefits": [
          "Eliminate local disk bottlenecks",
          "Direct cloud upload",
          "Simplified cloud migration workflows",
          "Support for all major cloud providers"
        ],
        "supportedTargets": [
          {
            "id": "s3",
            "name": "AWS S3",
            "provider": "Amazon Web Services",
            "features": ["S3-compatible storage support", "Multi-region"]
          },
          {
            "id": "abs",
            "name": "Azure Blob Storage",
            "provider": "Microsoft Azure",
            "features": ["Hot/Cool/Archive tiers"]
          },
          {
            "id": "adls",
            "name": "Azure Data Lake Storage Gen2",
            "provider": "Microsoft Azure",
            "features": ["Hierarchical namespace", "Big data analytics"]
          },
          {
            "id": "gcs",
            "name": "Google Cloud Storage",
            "provider": "Google Cloud Platform",
            "features": ["Multi-regional storage"]
          },
          {
            "id": "onelake",
            "name": "Microsoft OneLake",
            "provider": "Microsoft Fabric",
            "features": ["Unified data lake", "Fabric integration"]
          },
          {
            "id": "local",
            "name": "Local File System",
            "provider": "On-Premises",
            "features": ["Network shares", "Local disks"]
          }
        ]
      }
    ],
    "summary": {
      "totalFeatures": 7,
      "categories": ["Performance", "Simplicity", "Operations", "Security", "Flexibility", "Cloud"],
      "mostPopular": ["parallel-export", "single-executable", "cloud-integration"]
    }
  },
  "metadata": {
    "lastUpdated": "2026-02-19",
    "purpose": "Feature catalog for AI agents",
    "schemaVersion": "1.0.0"
  }
}