3. Data, Science & AI

Tracks machine learning experiments, hyperparameters, and metrics using MLflow and wandb.

Reduces token usage in AI conversations through context compression and summarization for efficient long-session management.

Evaluates large language models (LLMs) using standardized benchmarks such as MMLU, HumanEval, and GSM8K, and sets up evaluation pipelines.

Provides tools for crafting, optimizing, and deploying effective prompts for LLMs, including RAG systems and agent workflows.

Enables creation of AI agents, multi-agent systems, and agent workflows using Google's ADK framework in Python.

Enforces best practices for MariaDB database development, including Galera cluster configuration and MariaDB-specific features.

Provides AI-driven code, architecture, and UI/UX feedback via Google Gemini CLI for external critique and design alternatives.

Adds AI-generated metadata to a local BTR knowledge tree for intelligent context organization and retrieval.

AI-powered question answering for custom applications, generating personalized responses using user context and company-specific knowledge bases.

Assists in database schema design, normalization, and data modeling to optimize data storage and retrieval efficiency.

Optimizes LLM model reasoning, regeneration, and debugging processes for enhanced AI development efficiency.

Crafts optimized prompts for AI sub-agents, slash commands, and system instructions using Claude 4.x patterns and context engineering.

Provides step-by-step guidance for proper conda environment and package management within the opencode project context.

Builds and manages ETL pipelines, data warehouses, and data lakes for scalable data processing and storage solutions.

Matches user profiles to job requirements using semantic analysis to evaluate candidate-job fit.

Provides end-to-end machine learning model development, experimentation, and data analysis capabilities for scientific and business applications.

Provides MongoDB best practices for schema design, indexing, and query optimization to improve database performance and structure.

Provides growth analytics capabilities including cohort analysis, funnel analysis, and growth metric tracking for business optimization.

Provides Redis best practices for data modeling, caching patterns, and performance optimization.

Monitors real-time AI model training progress, displaying live metrics and dashboard views for ongoing experiments.

Analyzes machine learning training logs to interpret loss curves and diagnose training behavior in completed runs.

Optimizes SQL queries and database performance for PostgreSQL, MySQL, and SQLite, including schema design and tuning.

Tool for designing rigorous scientific experiments, including hypothesis testing and ablation studies in AI/ML research.

Automates hyperparameter search to optimize machine learning model performance through systematic exploration of learning rate and batch size.