AI at work
Understand workflows, knowledge bases and business conversations.
- Retrieval-Augmented Generation
A method that retrieves relevant information before an AI generates an answer.
- Large Language Model
An AI model that understands and generates language.
- Prompt
The question, instruction and context you give an AI.
- Token
A basic chunk of text that a model processes.
- 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.
- Application Programming Interface
A defined way for software to exchange data or call each other's capabilities.
- Hallucination
An AI response that sounds plausible but is false or unsupported.
- Transformer
A neural-network architecture that models relationships in sequences and underpins modern LLMs.
- Attention Mechanism
A mechanism that lets a model focus dynamically on the most relevant parts of its input.
- Quantization
A technique that represents model values with lower precision to reduce memory and inference cost.
- Artificial Intelligence
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Machine Learning
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Deep Learning
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Supervised Learning
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Unsupervised Learning
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Reinforcement Learning
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Neural Network
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Dataset
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Training Data
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.
- Label
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Model
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Prediction
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Classification
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.
- Computer Vision
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Natural Language Processing
A core concept for explaining how AI systems learn from data, make predictions or complete tasks.
- Linear Algebra
A mathematical or data concept used to represent information, measure model error or improve training.
- 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.
- Covariance
A mathematical or data concept used to represent information, measure model error or improve training.
- Gradient
A mathematical or data concept used to represent information, measure model error or improve training.
- Gradient Descent
An optimisation method that repeatedly adjusts model parameters to reduce prediction error.
- Loss Function
A mathematical or data concept used to represent information, measure model error or improve training.
- Objective 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.
- Learning Rate
A mathematical or data concept used to represent information, measure model error or improve training.
- Regularization
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.
- Bias-Variance Tradeoff
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.
- Perceptron
A building block or training mechanism used inside neural networks.
- Neuron
A building block or training mechanism used inside neural networks.
- Activation Function
A building block or training mechanism used inside neural networks.
- ReLU
A building block or training mechanism used inside neural networks.
- Sigmoid
A building block or training mechanism used inside neural networks.
- Softmax
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.
- Backpropagation
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.
- Dropout
A building block or training mechanism used inside neural networks.
- Batch Normalization
A building block or training mechanism used inside neural networks.
- Convolutional Neural Network
A building block or training mechanism used inside neural networks.
- Recurrent Neural Network
A building block or training mechanism used inside neural networks.
- Long Short-Term Memory
A building block or training mechanism used inside neural networks.
- Gated Recurrent Unit
A building block or training mechanism used inside neural networks.
- Encoder-Decoder
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.
- Byte Pair Encoding
A concept used to represent, process or generate human language with machine-learning models.
- WordPiece
A concept used to represent, process or generate human language with machine-learning models.
- SentencePiece
A concept used to represent, process or generate human language with machine-learning models.
- Positional Encoding
A concept used to represent, process or generate human language with machine-learning models.
- Self-Attention
A concept used to represent, process or generate human language with machine-learning models.
- Multi-Head Attention
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.
- Masked Language Model
A concept used to represent, process or generate human language with machine-learning models.
- Causal Language Model
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.
- Generative Pre-trained Transformer
A concept used to represent, process or generate human language with machine-learning models.
- Foundation Model
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- 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.
- Mixture of Experts
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Sparse 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.
- Generative Adversarial Network
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Variational Autoencoder
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Autoencoder
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Vision Transformer
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Graph Neural Network
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.
- Retrieval Model
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Reranker
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Cross-Encoder
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Bi-Encoder
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Knowledge Distillation
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Pruning
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Model Merging
A model architecture or technique that shapes how an AI system represents, generates or retrieves information.
- Ensemble Learning
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.
- Reinforcement Learning from Human Feedback
A method or artifact used to train a model and adapt its behavior to a task.
- Direct Preference Optimization
A method or artifact used to train a model and adapt its behavior to a task.
- Low-Rank Adaptation
A method or artifact used to train a model and adapt its behavior to a task.
- Parameter-Efficient 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.
- Domain Adaptation
A method or artifact used to train a model and adapt its behavior to a task.
- Curriculum 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.
- Hyperparameter Tuning
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.
- Learning Rate Schedule
A method or artifact used to train a model and adapt its behavior to a task.
- Data Labeling
A method or artifact used to train a model and adapt its behavior to a task.
- Annotation
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.
- Inference
A setting or system component that affects how a trained model produces and serves outputs.
- Decoding
A setting or system component that affects how a trained model produces and serves outputs.
- Greedy Decoding
A setting or system component that affects how a trained model produces and serves outputs.
- Beam Search
A setting or system component that affects how a trained model produces and serves outputs.
- Temperature
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.
- Max Tokens
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.
- KV Cache
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.
- Continuous 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.
- Latency
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.
- Endpoint
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.
- Reciprocal Rank Fusion
A component or method used to find, rank and ground information for an AI answer.
- On-device Inference
A setting or system component that affects how a trained model produces and serves outputs.
- Prompt Engineering
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- System Prompt
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- User Prompt
A concept for giving instructions, context, structure or safety boundaries to a generative model.
- 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.
- Role Prompting
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.
- Instruction Hierarchy
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.
- Keyword Search
A component or method used to find, rank and ground information for an AI answer.
- Hybrid 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.
- Cosine Similarity
A component or method used to find, rank and ground information for an AI answer.
- Approximate Nearest Neighbor
A component or method used to find, rank and ground information for an AI answer.
- Vector Index
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.
- Ranker
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.
- Citation
A component or method used to find, rank and ground information for an AI answer.
- Knowledge Base
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.
- Tool
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Workflow
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Orchestration
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Autonomous Agent
A component or pattern for letting an AI system plan, use tools and complete multi-step work.
- Multi-agent System
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.
- Agent Evaluation
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.
- Prompt Template
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.
- Area Under the Curve
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- Perplexity
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- BLEU
A concept for measuring quality, reliability, risk or responsibility in an AI system.
- ROUGE
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.
- Adversarial Attack
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.
- Responsible AI
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.
- Image Generation
A method or capability for working with images, audio, video or multiple data types.
- Text-to-Image
A method or capability for working with images, audio, video or multiple data types.
- Text-to-Video
A method or capability for working with images, audio, video or multiple data types.
- Text-to-Speech
A method or capability for working with images, audio, video or multiple data types.
- Speech-to-Text
A method or capability for working with images, audio, video or multiple data types.
- Automatic Speech Recognition
A method or capability for working with images, audio, video or multiple data types.
- Optical Character 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.
- Latent Diffusion
A method or capability for working with images, audio, video or multiple data types.
- Stable 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.
- Inpainting
A method or capability for working with images, audio, video or multiple data types.
- Outpainting
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.
- Video Generation
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.
- Data Drift
An engineering practice or platform component for building, deploying and operating AI systems.
- Concept Drift
An engineering practice or platform component for building, deploying and operating AI systems.
- Feature Store
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.
- Kubernetes
An engineering practice or platform component for building, deploying and operating AI systems.
- Graphics Processing Unit
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.
- Distributed Training
An engineering practice or platform component for building, deploying and operating AI systems.
- Federated Learning
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.