AI Coding Glossary

The AI Coding Glossary is a comprehensive collection of common AI coding concepts and terms. It’s a quick reference for both beginners and experienced developers looking for definitions and refreshers related to AI coding.

It covers the fundamental concepts, terminology, and patterns that are essential for understanding AI-assisted programming. From core machine-learning concepts like transformers and tokenization to practical coding patterns like prompt engineering and chain of thought (CoT), this glossary helps you navigate the vocabulary of AI programming.

Whether you’re working with large language models (LLMs), implementing RAG systems, or optimizing prompts for better code generation, these terms form the foundation of modern AI-enhanced development practices.

  • activation function A nonlinear mapping applied to neuron inputs that enables neural networks to learn complex relationships.
  • agent A system that perceives, decides, and acts toward goals, often looping over steps with tools, memory, and feedback.
  • agentic coding An approach to software development in which AI agents plan, write, run, and iteratively improve code.
  • artificial intelligence (AI) The field of building machines and software that perform tasks requiring human-like intelligence.
  • attention mechanism A neural network operation that computes a weighted sum of value vectors based on the similarity between a query and a set of keys.
  • context engineering The systematic design and optimization of the information given to a model at inference time so it can answer effectively.
  • context window The maximum span of tokens that a language model can consider at once.
  • convolutional network A neural network that uses local receptive fields and shared weights to process structured signals such as images.
  • fine-tuning The process of adapting a pre-trained model to a new task or domain.
  • function calling A model feature that lets the model choose a tool and emit JSON arguments so your app runs the API call and returns results.
  • generative model A model that learns a data distribution so it can generate new samples or assign probabilities to observations.
  • generative pre-trained transformer (GPT) Autoregressive language models that use the transformer architecture and are pre-trained on large text corpora.
  • guardrails Application-level policies and controls that constrain how a model or agent behaves.
  • hallucination When a generative model produces confident but false or unverifiable content and presents it as fact.
  • large language model (LLM) A neural network that predicts the next token to perform general-purpose language tasks.
  • loss function A scalar objective that measures prediction error and shapes gradients to guide model training.
  • machine learning A subfield of AI that builds models that improve their performance on a task by learning patterns from data.
  • Model Context Protocol (MCP) An open, client-server communication standard that lets AI applications connect to external tools and data sources.
  • natural language processing (NLP) A field of computer science and artificial intelligence that enables computers to analyze, interpret, generate, and interact with human language in text and speech.
  • neural network A computational model composed of layered, interconnected units that learn learn input-to-output mappings.
  • parameter A learned internal value of a model, such as a weight or bias.
  • prompt The input text or a structured message that tells a generative model what to do.
  • prompt engineering The practice of designing and refining prompts for generative models.
  • prompt injection An attack where adversarial text is crafted to steer a model or model-integrated app into ignoring its original instructions and performing unintended actions.
  • recurrent neural network (RNN) A neural network that processes sequences by applying the same computation at each step.
  • reinforcement learning A learning approach where an agent improves decisions by interacting with an environment and maximizing cumulative reward.
  • retrieval-augmented generation (RAG) A technique that improves a model’s outputs by retrieving relevant external documents at query time and feeding them into the model.
  • self-attention A mechanism that compares each token to all others and mixes their information using similarity-based weights.
  • system prompt A message that establishes a model’s role, goals, constraints, and style before user inputs.
  • tagging The process of assigning one or more discrete labels to data items so that models and tools can learn from them.
  • temperature A decoding parameter that rescales model logits before sampling.
  • tensor parameter A learned multi-dimensional array that a model updates during training to shape its computations.
  • text corpora Curated collections of machine-readable text that serve as data resources for linguistics and natural language processing.
  • token A minimal unit of text used by NLP systems and language models.
  • tokenization The process of converting raw text into a sequence of discrete tokens.
  • training The process of fitting a model’s parameters to data by minimizing a loss function.
  • transformer A neural network model that uses self-attention to handle sequences without recurrence or convolutions.
  • transformer architecture A neural network design that models sequence dependencies using self-attention instead of recurrence or convolutions.
  • vibe coding An AI-assisted programming style where a developer describes goals in natural language and accepts model-generated code with minimal manual editing.
  • weight A learned scalar or tensor that scales signals in a model and is updated during training to shape predictions.
Reference Share Feedback