Search AI Encyclopedia
Search across entries, definitions, categories, and tags.
35 results
Generative AI (GenAI)
A category of artificial intelligence models that can produce new text, images, code, or audio based on patterns learned from existing data.
AI Agents & Agentic Workflows
Autonomous or semi-autonomous AI systems designed to achieve specific goals by planning, reasoning, and using tools to take actions in digital environments.
AI Governance & Ethics
The frameworks, policies, and practices organizations use to manage the risks and ethical implications of developing and deploying AI systems.
Artificial Intelligence (AI)
Computer systems designed to perform tasks that typically require human intelligence, such as learning, reasoning, perception, or decision-making.
Machine Learning (ML)
A field of AI where systems learn patterns from data to make predictions or decisions without being explicitly programmed for every rule.
Large Language Model (LLM)
A neural network trained on large text datasets to predict and generate human-like language.
Retrieval-Augmented Generation (RAG)
A technique that augments model responses with retrieved context from trusted data sources.
Prompt Engineering
Designing and iterating prompts to guide AI models toward reliable, useful outputs.
Model Evaluation
The process of measuring model performance, quality, and safety using defined metrics and test sets.
Vector Database
A database optimized to store and search vector embeddings for similarity-based retrieval.
Fine-Tuning (PEFT, LoRA)
The process of taking a pre-trained model and training it further on a smaller, specialized dataset to adapt it to specific tasks or domains.
Embeddings
Mathematical representations of data (like text or images) as lists of numbers, enabling models to measure similarity and understand meaning.
Context Window
The maximum amount of text (measured in tokens) that an AI model can process at one time.
Hallucination
Instances where an AI model generates false, nonsensical, or unverified information, presenting it confidently as fact.
Grounding
The practice of tying an AI model’s responses directly to verifiable, factual data sources (like a company database or web search) to prevent hallucinations.
MLOps
Machine Learning Operations (MLOps) is a set of practices that aims to deploy and maintain machine learning models in production reliably and efficiently.
Deep Learning
A subset of machine learning based on artificial neural networks with multiple layers.
Natural Language Processing (NLP)
A branch of artificial intelligence focused on enabling computers to understand, interpret, and generate human language.
Inference
The process of running live data through a trained machine learning model to make a prediction or generate an output.
Tokens & Tokenization
The base units of data processed by an LLM. A token is typically a chunk of characters rather than a full word.
Parameters (Weights)
The internal variables a neural network learns during training. They act as the "knowledge" of the model.
Prompt Injection / Jailbreaking
A security vulnerability where malicious input causes an LLM to ignore its original instructions and execute unauthorized actions.
Red Teaming
The practice of aggressively testing AI systems by simulating adversarial attacks to identify flaws, biases, or vulnerabilities.
Data Bias / Drift
Systematic errors in an AI model output stemming from disproportionate, skewed, or outdated training data.
Semantic Search
A search technique that aims to understand the user’s intent and the contextual meaning of terms, rather than relying on exact keyword matches.
API
A set of rules and protocols that allows different software applications to communicate with each other.
Mixture of Experts (MoE)
An AI architecture that replaces a single dense neural network with multiple specialized sub-networks (experts) to improve efficiency and scale.
Transformer Architecture
The neural network architecture introduced in 2017 that powers virtually all modern large language models through self-attention mechanisms.
Chain-of-Thought Prompting
A prompting technique that instructs an AI model to reason step-by-step before arriving at a final answer, significantly improving accuracy on complex tasks.
Function Calling (Tool Use)
A capability that allows LLMs to invoke structured external tools or APIs mid-conversation, enabling reliable real-world actions and grounded data retrieval.
Foundation Models
Large AI models trained on broad, general datasets at massive scale, designed to be adapted for a wide range of downstream tasks.
Reinforcement Learning from Human Feedback (RLHF)
A training technique that uses human preference ratings to fine-tune AI models to produce more helpful, accurate, and safe responses.
Computer Vision
A field of AI that enables machines to interpret and understand visual information from images and video.
Multimodal AI
AI systems that can process and generate content across multiple modalities—text, images, audio, and video—within a single model.
AI Workflow Automation
The use of AI models, agents, and integrations to automate multi-step business processes that previously required human judgment.