3. Data, Science & AI

Regenerates web JSON data from raw sources after parser script modifications, ensuring data consistency and freshness.

Tracks data lineage and provenance to map data flow, dependencies, and assess impact of changes in data pipelines.

Provides data lifecycle management strategies to optimize storage costs, system performance, and legal compliance.

Provides best practices for data modeling, testing, and production workflows using dbt (Data Build Tool) to optimize data transformation pipelines.

Real-time dashboard visualizing multi-agent interactions, tool usage, and session flows in Claude Code with swim lanes and live charts.

Optimizes AI context formatting to be concise, structured, and token-efficient, enhancing model performance and reducing costs.

Comprehensive guide to Apache Kafka for real-time data streaming, covering topics, producers, consumers, stream processing, and production best practices.

Guides A/B and multivariate experiment design, statistical significance validation, and data-driven product decision analysis.

Enforces evidence-first summarization rules starting with data to reduce token consumption and improve reliability in AI-generated content.

Maps data flow from source to destination, enabling transparency, impact analysis, and troubleshooting in data systems.

Enables semantic and similarity search implementations using vector embeddings and vector databases for efficient data retrieval.

Guides strategic planning for clinical lab data product portfolios including reports, dashboards, and stakeholder-aligned data governance.

Enables formal data agreements between producers and consumers to guarantee data quality, consistency, and reliability in data pipelines.

Monitors and optimizes data pipeline performance to ensure timely data availability for analytics and business operations.

Provides a comprehensive guide for validating data quality, implementing testing frameworks, detecting anomalies, and ensuring observability in production data pipelines.

Builds AI agents and assistants with Convex, enabling RAG, tool-calling, and LLM integration for chat interfaces and conversation threads.

Provides comprehensive Explainable AI (XAI) capabilities for interpreting and validating AI/ML model decisions and outputs.

Provides strategies for optimizing costs in LLM applications, covering token economics and RAG architecture design.

Manages schema drift in data pipelines by detecting and resolving structural changes to maintain data consistency and integrity.

Comprehensive guide to creating and integrating regression benchmarks for AI systems, including test suite creation and continuous benchmarking strategies.

Provides a reference framework for generating, compiling, and linting AI prompts to ensure compliance with the Agnostic Prompt Standard (APS) v1.0.

Enables human intervention in AI decision-making with comprehensive tracking, auditing, and feedback loops for accountability and system improvement.

Comprehensive guide covering database transactions, ACID properties, isolation levels, locking mechanisms, and distributed transaction management.

Executes Python code in a sandbox for data analysis, visualization, and automated report generation including Excel, Word, and PDF outputs.