Intermediate
Builds on core AI concepts
- Retrieval-Augmented Generation
A method that retrieves relevant information before an AI generates an answer.
- AI Agent
An AI system that plans steps, uses tools and works toward a goal.
- Embedding
A numeric representation of text, images or other content that computers can compare.
- Vector Database
A database built to store and search vector data.
- Context Window
The amount of text a model can consider in one request.
- Fine-tuning
Further training an existing model on focused data for a particular task.
- Model Context Protocol
An open protocol for connecting AI applications to tools and external data in a consistent way.
- Reinforcement Learning
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Validation Data
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Test Data
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Feature
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Regression
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Clustering
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Probability
A mathematical or data concept used to represent information, measure model error or improve training.
- Distribution
A mathematical or data concept used to represent information, measure model error or improve training.
- Statistics
A mathematical or data concept used to represent information, measure model error or improve training.
- Mean
A mathematical or data concept used to represent information, measure model error or improve training.
- Variance
A mathematical or data concept used to represent information, measure model error or improve training.
- Loss Function
A mathematical or data concept used to represent information, measure model error or improve training.
- Optimization
A mathematical or data concept used to represent information, measure model error or improve training.
- Overfitting
A mathematical or data concept used to represent information, measure model error or improve training.
- Underfitting
A mathematical or data concept used to represent information, measure model error or improve training.
- Normalization
A mathematical or data concept used to represent information, measure model error or improve training.
- Standardization
A mathematical or data concept used to represent information, measure model error or improve training.
- Data Augmentation
A mathematical or data concept used to represent information, measure model error or improve training.
- Neuron
A building block or training mechanism used inside neural networks.
- Weight
A building block or training mechanism used inside neural networks.
- Bias
A building block or training mechanism used inside neural networks.
- Epoch
A building block or training mechanism used inside neural networks.
- Batch
A building block or training mechanism used inside neural networks.
- Batch Size
A building block or training mechanism used inside neural networks.
- Mini-batch
A building block or training mechanism used inside neural networks.
- Tokenization
A concept used to represent, process or generate human language with machine-learning models.
- Tokenizer
A concept used to represent, process or generate human language with machine-learning models.
- Vocabulary
A concept used to represent, process or generate human language with machine-learning models.
- Encoder
A concept used to represent, process or generate human language with machine-learning models.
- Decoder
A concept used to represent, process or generate human language with machine-learning models.
- BERT
A concept used to represent, process or generate human language with machine-learning models.
- Base Model
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Multimodal Model
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Diffusion Model
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Knowledge Graph
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Pre-training
A method or artifact used to train a model and adapt its behavior to a task.
- Instruction Tuning
A method or artifact used to train a model and adapt its behavior to a task.
- Supervised Fine-tuning
A method or artifact used to train a model and adapt its behavior to a task.
- Transfer Learning
A method or artifact used to train a model and adapt its behavior to a task.
- Hyperparameter
A method or artifact used to train a model and adapt its behavior to a task.
- Checkpoint
A method or artifact used to train a model and adapt its behavior to a task.
- Early Stopping
A method or artifact used to train a model and adapt its behavior to a task.
- Synthetic Data
A method or artifact used to train a model and adapt its behavior to a task.
- Alignment
A method or artifact used to train a model and adapt its behavior to a task.
- Decoding
A setting or system component that affects how a trained model produces and serves outputs.
- Top-p Sampling
A setting or system component that affects how a trained model produces and serves outputs.
- Top-k Sampling
A setting or system component that affects how a trained model produces and serves outputs.
- Stop Sequence
A setting or system component that affects how a trained model produces and serves outputs.
- Batching
A setting or system component that affects how a trained model produces and serves outputs.
- Throughput
A setting or system component that affects how a trained model produces and serves outputs.
- Tokens per Second
A setting or system component that affects how a trained model produces and serves outputs.
- Model Serving
A setting or system component that affects how a trained model produces and serves outputs.
- Autoscaling
A setting or system component that affects how a trained model produces and serves outputs.
- Few-shot Prompting
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Zero-shot Prompting
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Chain of Thought
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Prompt Chaining
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Structured Output
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Function Calling
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Tool Calling
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- JSON Schema
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Context Engineering
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Prompt Injection
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Jailbreak
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Guardrail
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Grounding
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- Retrieval
A component or method used to find, rank and ground information for an AI answer.
- Semantic Search
A component or method used to find, rank and ground information for an AI answer.
- Similarity Search
A component or method used to find, rank and ground information for an AI answer.
- Chunking
A component or method used to find, rank and ground information for an AI answer.
- Document Splitting
A component or method used to find, rank and ground information for an AI answer.
- Metadata Filtering
A component or method used to find, rank and ground information for an AI answer.
- Retrieval Query
A component or method used to find, rank and ground information for an AI answer.
- Query Rewriting
A component or method used to find, rank and ground information for an AI answer.
- Document Ingestion
A component or method used to find, rank and ground information for an AI answer.
- Orchestration
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Planning
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Task Decomposition
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Memory
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Short-term Memory
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Long-term Memory
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Tool Use
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Human in the Loop
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Agentic Workflow
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Resource
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Client-Server Architecture
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Benchmark
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Evaluation
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Metrics
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Accuracy
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Precision
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Recall
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- F1 Score
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Factuality
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Robustness
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Red Teaming
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Content Moderation
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Fairness
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Explainability
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Automatic Speech Recognition
A method or capability for working with images, audio, video or multiple data types.
- Image Captioning
A method or capability for working with images, audio, video or multiple data types.
- Visual Question Answering
A method or capability for working with images, audio, video or multiple data types.
- Diffusion
A method or capability for working with images, audio, video or multiple data types.
- ControlNet
A method or capability for working with images, audio, video or multiple data types.
- Image Embedding
A method or capability for working with images, audio, video or multiple data types.
- Voice Cloning
A method or capability for working with images, audio, video or multiple data types.
- Synthetic Media
A method or capability for working with images, audio, video or multiple data types.
- Deepfake
A method or capability for working with images, audio, video or multiple data types.
- MLOps
An engineering practice or platform component for building, deploying and operating AI systems.
- Pipeline
An engineering practice or platform component for building, deploying and operating AI systems.
- Experiment Tracking
An engineering practice or platform component for building, deploying and operating AI systems.
- Model Registry
An engineering practice or platform component for building, deploying and operating AI systems.
- Model Versioning
An engineering practice or platform component for building, deploying and operating AI systems.
- Model Monitoring
An engineering practice or platform component for building, deploying and operating AI systems.
- Model Deployment
An engineering practice or platform component for building, deploying and operating AI systems.
- Continuous Integration and Continuous Delivery
An engineering practice or platform component for building, deploying and operating AI systems.
- Containerization
An engineering practice or platform component for building, deploying and operating AI systems.
- Docker
An engineering practice or platform component for building, deploying and operating AI systems.
- Tensor Processing Unit
An engineering practice or platform component for building, deploying and operating AI systems.
- Edge AI
An engineering practice or platform component for building, deploying and operating AI systems.