3. Data, Science & AI

Configures and manages retention calculation operations for data analytics, enabling user retention analysis.

Automates creation of dbt tests for data pipelines, enabling efficient validation of data transformations and ensuring data quality in ETL processes.

Processes and analyzes blockchain data including blocks, transactions, and smart contracts through query execution.

Optimizes Granola's transcription accuracy and processing performance, reducing latency and improving output quality.

Enables real-time streaming transcription via Deepgram API for live audio processing, voice interfaces, and voice-controlled applications.

Automates machine learning model deployment to production, implementing best practices for serving, performance, and error handling via API.

Provides SQL query performance analysis and optimization guidance to improve database speed and efficiency.

Analyzes database query performance using EXPLAIN plans to identify bottlenecks and provide optimization recommendations for faster execution.

Manages custom prompt libraries for Cascade, enabling creation, organization, and activation of AI prompt templates via specific trigger phrases.

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

Profiles inference latency in machine learning model deployments. Auto-activating tool for optimizing ML inference performance.

Analyzes SQL queries to identify bottlenecks and suggests optimizations including index recommendations and query rewrites for improved database performance.

Creates a minimal LangChain example for starting integrations, testing setups, or learning basic chains and prompts.

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

Diagnoses and resolves common errors in Kling AI API usage, particularly for failed video generation and API connectivity issues.

Coordinates multi-agent systems with handoffs, routing, and workflows across AI providers for complex AI application development.

Executes operations for connecting to and managing feature stores in machine learning deployment pipelines.

Constructs personalized recommendation systems using collaborative, content-based, or hybrid filtering techniques to analyze user preferences and item features.

Programmatically queries the OpenRouter model catalog to list available AI models and check their status for integration purposes.

Automates PyTorch model training operations, providing streamlined configuration and execution for machine learning workflows.

Explains machine learning model predictions, feature importance, and behavior using SHAP and LIME techniques.

Automates machine learning model deployment to production, implementing best practices for serving, performance optimization, and error handling.

Automates data quality checks within data pipelines, ensuring data integrity and reliability through predefined validation rules.

Creates ROC curve visualizations to evaluate classification model performance metrics in machine learning workflows.