3. Data, Science & AI

Designs database schemas and writes optimized queries for PostgreSQL and MongoDB, covering SQL/NoSQL operations, aggregation, and performance tuning.

Orchestrates multi-agent collaboration to decompose and solve large-scale technical tasks through coordinated AI workflows.

Builds and maintains scalable data pipelines for efficient extraction, transformation, and loading of data across infrastructure systems.

Assists in database design, schema migrations, data integrity enforcement, and API standardization for data systems.

Designs, tests, and optimizes AI prompts and agent instructions to enhance model performance and output quality.

Analyzes NetSuite data for professional services organizations, focusing on project profitability, resource utilization, and financial metrics using MCP tools.

Guide for creating MCP servers to integrate external APIs with LLMs, supporting Python (FastMCP) and Node/TypeScript (MCP SDK).

Creates custom subagents for specialized AI tasks including code reviewers, debuggers, and domain-specific assistants with tailored prompts.

Retrieves structured geographic data including city, state, country, coordinates, and timezone for location queries.

Provides personalized movie and TV show recommendations by analyzing Plex viewing history using machine learning.

Retrieves current weather conditions and forecasts for any location using external weather APIs.

Performs semantic search on a RAG vector database to retrieve relevant document chunks and context using embeddings for LLM applications.

Provides ingestion progress reports and statistics for Plex media library monitoring and summary insights.

Provides quick health checks for RAG databases by retrieving document counts, word totals, unique sources, and ingestion progress.

Splits large texts into chunks, summarizes segments, and merges results for efficient document processing using AI workflows.

Ingests text and Plex media into a RAG vector database for AI retrieval, supporting batch processing and subtitle management.

Diagnoses RAG pipelines for missing data, ingestion errors, and entry issues to ensure optimal LLM retrieval performance.

Enables semantic search within Plex media libraries for movies and TV shows using natural language queries on title, actor, genre, or description.

Processes Plex media items for RAG systems, supporting granular, batch, and parallel ingestion with subtitle extraction.

Retrieves a single knowledge base entry using its unique ID for inspection or viewing.

Enables concept-level search in knowledge bases using embedding-based semantic similarity for relevant information retrieval without exact keyword matching.

Locates specific scenes in movies or TV shows by searching subtitle files for quotes or moments.

Manages AI agent lifecycle through usage tracking, prompt versioning, and health monitoring for performance optimization and traceability.

Generates context-aware response suggestions and auto-replies for inbound messages using AI Orchestrator technology.