3. Data, Science & AI

Generates realistic test data and SQL seed scripts for database population in development and testing environments.

Configures cross-validation setups for machine learning model training. Auto-activates on triggers like 'cross validation setup'.

Automates pivot table creation for data summarization and visualization in analytics workflows. Activates on triggers like 'pivot table creator' or 'pivot'.

Recalls project memories from previous sessions to provide context-aware assistance on decisions, conventions, and preferences.

Configures project-specific AI behavior through a .cursorrules file, enabling tailored AI interactions for development workflows.

Provides helper operations for configuring and using data visualization tools to represent data effectively for analysis.

Forecasts future values in time series data by analyzing historical trends, seasonality, and patterns using statistical and machine learning models.

Automates data pipeline creation and orchestration using Dagster, streamlining data workflow development and management.

Performs regression analysis on datasets, generating linear, polynomial, and other models with validation and performance metrics for predictive insights.

Builds and deploys production-ready generative AI agents with Vertex AI, Gemini models, RAG, and multi-modal capabilities on Google Cloud.

Executes PostHog's secondary workflow (Core Workflow B) to complement primary analytics use cases and handle user behavior tracking.

Automates cohort analysis report generation to track user retention patterns and behavioral trends for data-driven business decisions.

Automates configuration setup for NVIDIA Triton Inference Server in machine learning deployment pipelines.

Automates data catalog updates for data pipelines, ensuring metadata accuracy and consistency in data management systems.

Automates PySpark transformer operations in data pipelines for efficient data transformation workflows.

Automates and optimizes data compression operations in data pipelines for efficient storage and processing.

Optimizes deep learning models using Adam, SGD, and learning rate scheduling to enhance accuracy, reduce training time, and minimize resource usage.

Automates model pruning operations for efficient machine learning model deployment and optimization.

Builds production AI agents using Google's Agent Development Kit with Claude integration, React patterns, and multi-agent orchestration.

Automates database management, recovery, and optimization tasks for efficient data operations and configuration.

Builds asynchronous video generation pipelines with Kling AI for seamless integration into system workflows and scalable content production.

Configures incremental data load operations for data pipelines, enabling efficient data processing by loading only changed records.

Creates cohort analysis workflows to track user retention and behavior metrics in data analytics projects.

Automates dataset loader creation for machine learning training pipelines, enabling efficient data preparation and model input configuration.