3. Data, Science & AI

Enterprise Firebase platform with AI-driven Google Cloud and Context7 integrations for intelligent orchestration of scalable mobile and web applications.

Enterprise optimization for Claude Code's 200K token context window using strategic chunking, memory management, and MCP protocols.

End-to-end data science specialist for data processing, ML pipeline development, model deployment, and visualization using TensorFlow, PyTorch, and Scikit-learn.

Optimizes context persistence and knowledge retention for Claude Code sessions, enhancing AI coding assistance reliability.

Provides enterprise machine learning solutions including model development, AutoML, and MLOps for scalable production deployment.

Manages document data with CRUD operations, deduplication, and SQL access via CLI, Python API, or direct queries.

AI-driven system detecting user expertise through behavioral analysis and code complexity, enabling real-time adaptive guidance and tutorial personalization.

Generates intelligent Claude Code agents through requirement analysis, domain detection, model selection, and validation frameworks.

Enterprise AI-powered PostgreSQL platform with Context7 integration and intelligent branching for scalable data management and application development.

Provides SQL best practices including testing with pgTAP, linting via sqlfluff, query optimization, and migration management for PostgreSQL.

Enables creation, editing, and analysis of spreadsheets with support for formulas, formatting, data analysis, and visualization for various spreadsheet formats.

Enhances context7 integration with AI-powered features for advanced data processing and analysis.

Imports and processes markdown files into a database, including error correction and bulk import capabilities for content linking.

Automates web content ingestion by mapping sitemaps to discover URLs and selectively fetching content for data processing.

AI-powered extraction of structured metadata, content classification, and topic identification from documents with async batch processing support.

Enables automatic AI agent behavior adaptation using predefined behavioral archetypes based on work type classification.

Creates high-quality, domain-specific prompts through analysis, optimization, and validation engines for AI model interaction.

Collects content feedback and identifies patterns to inform rule updates, improving system accuracy and decision-making.

Offers a three-layer verification system (CoVe, HSP, RAG) to prevent AI hallucinations and ensure factual accuracy in generated content.

Provides expert guidance on data lake architecture, including partitioning, storage layout, schema design, and lakehouse patterns for scalable data organization.

Provides phase-aware context management for AI coder agents via checkpoint/restore to prevent token bloat in LLM interactions.

Enforces a mandatory four-step workflow for Databento API data acquisition: cost check, availability check, fetch, and validation to ensure quality and prevent errors.

Manages institutional knowledge and behavioral patterns for Wolf Agents, enabling skill-chaining and contextual AI agent interactions.

Analyzes Parquet file operations to suggest optimizations for compression, encoding, row group sizing, and statistics during read/write workflows.