3. Data, Science & AI

Automates transfer learning model adaptation, including fine-tuning and dataset-specific model adjustments.

Analyzes database query patterns to recommend optimal indexes and identify unused indexes for improved performance and storage efficiency.

Auto-activating anomaly detection for data analytics, using machine learning to identify outliers in real-time data streams.

Automates regression analysis setup and execution for data analytics workflows.

Creates interactive Plotly charts for data visualization. Automatically activates on chart-related triggers like 'plotly' or 'chart generator'.

Automates data transformation tasks in PySpark pipelines, enabling efficient big data processing workflows.

Checks OpenRouter model availability and implements fallback chains to maintain system resilience during AI model outages.

Automates machine learning model training by analyzing datasets, selecting model types, configuring parameters, and generating performance metrics using frameworks like scikit-learn.

Executes clustering algorithms (K-means, DBSCAN, hierarchical) on datasets to identify groups and analyze data structure.

Automates splitting datasets into training and testing sets for machine learning model development.

Performs text analysis including sentiment, keywords, and topics using NLP techniques for insight extraction from textual data.

Automates horizontal database sharding strategies to distribute data across shards for improved scalability and performance.

Analyzes database query patterns to recommend optimal indexes, improving performance and eliminating unused indexes to save storage.

Automates machine learning model optimization through hyperparameter tuning with grid search, random search, or Bayesian optimization.

Provides model interpretability and explainability for machine learning predictions, including feature importance and behavior insights.

Validates ethical implications and fairness of AI/ML models and datasets, providing bias detection and mitigation recommendations.

Configures Key Performance Indicator (KPI) definitions for data analytics workflows. Auto-activating helper for KPI setup and management.

Automates creation and management of data pipelines using Dagster for efficient data engineering workflows.

Optimizes LLM prompts to reduce token usage, lower costs, and improve performance through analysis and simplification.

Auto-activating tool for constructing funnel analysis visualizations and metrics from user event data.

Automates early stopping during ML training to prevent overfitting by monitoring validation metrics.

Automates creation, optimization, and evaluation of classification models using supervised learning with labeled data.

Processes images using computer vision for object detection, classification, and segmentation to provide user-requested insights.

Generates SQL window function operations for data analytics. Auto-activates on triggers like 'window function generator'.