AI Summary Hub

Glossary

Glossary of AI and ML terms used across the wiki.

A quick reference for key terms used in AI Summary Hub.

TermDefinition
A2AAgent2Agent protocol — open standard (Linux Foundation) for agent-to-agent interoperability across frameworks and vendors.
Agentic RAGRAG variant where the retrieval and generation steps are controlled by an autonomous agent that can iteratively plan and re-retrieve.
AgentSystem that perceives and acts toward goals.
Computer UseCapability allowing an LLM agent to control desktop GUIs (click, type, screenshot) as tools; Anthropic's term for its beta implementation in Claude.
Context EngineeringThe practice of designing, managing, and optimizing what information is placed in an LLM's context window — including retrieval, compression, and caching strategies.
CoTChain-of-thought — step-by-step reasoning elicited via prompting.
DPODirect Preference Optimization — post-training technique that fine-tunes a model on human preference pairs without a separate reward model.
Extended / Test-time computeScaling inference compute (e.g. more search steps, longer thinking) rather than training compute to improve model output quality at test time.
GraphRAGRAG variant that indexes documents as a knowledge graph, enabling multi-hop reasoning over entity relationships rather than flat vector retrieval.
GRPOGroup Relative Policy Optimization — RL-based post-training method (used in DeepSeek-R1) that improves reasoning by optimizing relative reward within a group of sampled outputs.
LLMLarge language model.
LLM-as-judgeEvaluation pattern where an LLM scores or ranks model outputs instead of (or alongside) human evaluators; used in automated evals and RLHF data pipelines.
MCPModel Context Protocol — open standard (Anthropic) that defines how LLM hosts connect to external tools, data sources, and APIs via a client–server interface.
RAGRetrieval-augmented generation — combining retrieval with LLM generation to ground responses in external knowledge.
ReActReasoning + acting in interleaved steps — thought–action–observation loop for tool-using agents.
RDDRetrieval-decision-design — spec-driven reasoning pattern that retrieves specifications, makes decisions aligned with them, and validates outputs.
RLHFReinforcement Learning from Human Feedback — post-training technique that uses human preference rankings to train a reward model, which then guides policy fine-tuning via RL.
SubagentAgent within a hierarchical agent system, delegated sub-tasks by an orchestrator.
TransformerNeural network architecture based on self-attention (e.g. BERT, GPT, Claude, Gemini).
Vibe codingInformal term for AI-assisted programming where the developer describes intent in natural language and lets an LLM generate the implementation with minimal manual coding.

See individual topic docs for detailed definitions and code examples.