Giao diện
Enterprise-grade, copy-paste runnable prompts for AI-assisted software engineering
Procedure to design, execute, and analyze controlled experiments (A/B tests) to validate the business impact of ML model...
Procedure to build a Retrieval-Augmented Generation (RAG) system using LangChain, connecting LLMs to private data via Ve...
Procedure to preprocess, normalize, and tokenize unstructured text data for Natural Language Processing (NLP) models.
Procedure to audit and optimize AI/ML codebases for performance, strict typing, and modern Python standards (beyond basi...
Procedure to package a trained Machine Learning model into a Docker container for deployment, ensuring reproducibility,...
Procedure to convert Machine Learning models (PyTorch, TensorFlow, Sklearn) to the Open Neural Network Exchange (ONNX) f...
Procedure to implement a centralized Feature Store to ensure training-serving skew is eliminated and features are reusab...
Procedure to identify and remove unused libraries, retired models, and feature flags to maintain security and build spee...
Procedure to wrap a Machine Learning model in a Flask REST API for real-time inference, including input validation and p...
Machine Learning workflow for Deploy Model to Endpoint.
Procedure to deploy a Machine Learning model to AWS SageMaker Endpoints, ensuring scalable, managed inference with Blue/...
Routine Documentation Update workflow specifically for AI & ML Engineering.
Procedure to identify and select the most relevant features for a machine learning model to reduce complexity and overfi...
Procedure to fine-tune Large Language Models using Low-Rank Adaptation (LoRA), enabling efficient customization on consu...
Procedure to optimize model configuration (hyperparameters) to maximize predictive performance.
Build a robust data ingestion pipeline for Retrieval Augmented Generation (RAG) that cleans, chunks, embeds, and indexes...
Procedure to explain machine learning model predictions (Global and Local importance) using SHapley Additive exPlanation...
Routine Knowledge Transfer workflow specifically for AI & ML Engineering.
Machine Learning workflow for Label Data with Active Learning.
Procedure to refactor experimental Jupyter Notebooks into modular, testable, and production-ready Python packages.
Procedure to detect model degradation (Data Drift / Concept Drift) over time, ensuring continued accuracy and triggering...
Machine Learning workflow for Optimize Hyperparameters.
Routine Performance Tuning workflow specifically for AI & ML Engineering.
Machine Learning workflow for Profile GPU Usage.