New research from Maximem. Agentic Context Management: Agent Memory is an architecture problem. Read the paper →

AI & LLM Glossary

Clear, practical definitions of AI concepts, from context windows to agentic memory. Built for engineering and product teams working with LLMs.

For the argument rather than the definitions, read the memory problem.

Showing 145 of 145 terms

A

Adherence (Instruction Adherence)

Measuring how well AI systems follow the specific instructions and constraints provided by users

EvalsSafety

Agent Observability

Monitoring and tracking what autonomous AI agents are doing in real-time across distributed systems.

Enterprise AIObservability

Agent Skills

Folders of markdown instructions an agent loads on demand to change how it performs a task, rather than what it knows.

AgentsKnowledge Systems

Agentic AI

AI systems that plan, call tools, evaluate the results, and decide what to do next, rather than producing a single response and stopping.

AgentsLLM Fundamentals

Agentic Memory System

A comprehensive memory framework for AI agents that maintains episodic, semantic, and procedural memory to enable learning and continuous improvement.

Memory & ContextAgents

AI Access Control

Systems determining who can use AI models, which data they can access, and what they're allowed to do.

Enterprise AICompliance

AI Agent

An autonomous system that perceives its environment, makes decisions, and takes actions to achieve specific goals without direct human intervention.

AgentsEnterprise AI

AI Auditability

The ability to create a complete record of what an AI system did, why it did it, and what inputs influenced its outputs.

Enterprise AICompliance

AI Bias

Systematic skew in model outputs that favors or disadvantages certain groups or answers, caused by patterns in training data, context, or system design.

SafetyCompliance

AI Cost Model

The framework for understanding and predicting how much your AI system will cost to operate at different scales.

Enterprise AIEconomics

AI Data Governance

Policies and systems controlling what data goes into AI models, how it's used, and who can access it.

Enterprise AICompliance

AI Plugins

Packaged extensions that give an AI assistant new abilities at runtime, spanning the original ChatGPT plugins through to MCP servers, agent skills, and apps.

AgentsInfrastructure

AI Traceability

The technical capability to follow an input through every transformation until it produces output, showing what influenced the result.

Enterprise AIObservability

AI Vendor Lock-In Risk

The danger of becoming dependent on a specific AI provider's models or infrastructure, making it costly to switch.

Enterprise AIEconomics

Alignment

Ensuring AI systems behave in accordance with human values, goals, and constraints

SafetyEnterprise AI

Alignment Evals

Testing whether AI system behavior aligns with specified goals, values, and constraints

EvalsSafety

API (Application Programming Interface)

A defined contract that lets one system call a specific function on another, with agreed inputs, outputs, and errors.

Infrastructure

Attention Mechanism

The operation that lets a model weigh every token against every other token, deciding what in the input matters for predicting what comes next.

LLM Fundamentals

Audit Log

Comprehensive records of AI system decisions, actions, and state changes for accountability and compliance

Enterprise AISafety

Autoresearch

Agents that run the research loop themselves, planning, searching, reading, synthesizing, and verifying until a question is actually answered

AgentsKnowledge Systems

C

Chain-of-Thought (CoT)

A prompting technique that makes LLMs show their reasoning step-by-step, improving accuracy especially on complex reasoning tasks.

LLM FundamentalsReasoning

Chunking

The process of dividing long documents into smaller pieces for RAG systems to store and retrieve efficiently.

Knowledge SystemsMemory & Context

Code Agent

AI agents specialized in writing, analyzing, and executing code to solve problems programmatically

Agents

Compliance

Ensuring AI systems adhere to applicable laws, regulations, industry standards, and ethical guidelines.

ComplianceEnterprise AI

Context Compression

Reducing the token size of context information while preserving critical details and meaning

Memory & Context

Context Engineering

The discipline of deciding what information goes into a model's context window, in what order, and in what form, drawn from a much larger pool of available information.

Memory & ContextLLM Fundamentals

Context Eviction

Removing or deprioritizing old information from the AI's active context to make room for new data

Memory & Context

Context Management

Strategically selecting what information an AI system should consider in each interaction

Memory & Context

Context Retrieval

Fetching relevant past information or memories to include in current AI processing

Memory & Context

Context Rot

Degradation of memory quality and accuracy as stored context becomes outdated or semantically disconnected

Memory & Context

Context Window

The maximum amount of text an LLM can consider at once, measured in tokens.

LLM FundamentalsMemory & Context

Coordination Protocol

The rules and standards enabling multiple AI agents to work together, share information, and synchronize actions.

AgentsArchitecture

Cost-to-Completion

The total cost, in money or tokens, required to accomplish a task using AI, from initial attempt to satisfactory result.

EconomicsAgents

Cross-Encoder Scoring

Using transformer models to score query-document pairs directly rather than encoding them separately

Knowledge Systems

Customization

Tailoring AI systems to specific organizational needs, preferences, and constraints without rebuilding from scratch.

Enterprise AI

D

Data Catalog

An inventory of the datasets an organization holds, recording what exists, who owns it, where it lives, and what it contains.

Data EngineeringKnowledge Systems

Data Lineage

The record of where data came from and how it was transformed on the way to where it is now.

Data EngineeringCompliance

Data Observability

Continuous monitoring of whether data is healthy right now: freshness, volume, schema drift, distribution shifts, and anomalies.

Data EngineeringObservability

Data Product

Data packaged with a contract: defined schema, named owner, service levels, access policy, and documentation, so consumers can depend on it.

Data EngineeringEnterprise AI

Data Sovereignty (AI Context)

The principle that data, especially when used in AI systems, should remain under the control and jurisdiction of its origin country or organization.

ComplianceEnterprise AI

Dataset

A collection of raw or lightly processed data, defined by its contents rather than by any contract about quality, ownership, or support.

Data EngineeringLLM Fundamentals

Delegation

Agents assigning subtasks to other agents or systems, breaking complex problems into manageable pieces

Agents

Dense Retrieval

Using learned embeddings to retrieve information based on semantic similarity rather than keyword matching

Knowledge Systems

Deployment

The process of taking a trained AI model or application from development into production where it serves real users.

Infrastructure

Developer Agents

AI agents designed to autonomously write, test, debug, and optimize code, assisting software engineers in development tasks.

Agents

Distributed Systems

Computing architectures where AI systems are spread across multiple machines or locations, enabling scale, reliability, and geographic distribution.

Infrastructure

Document Ranking

Sorting retrieved documents by relevance to the query using scoring or learning-to-rank models

Knowledge Systems

E

Embedding Drift

Changes in embedding model output distributions or quality over time, degrading retrieval performance

Knowledge Systems

Embeddings

Numerical representations of text that capture semantic meaning, enabling AI systems to understand similarity and relationships.

LLM FundamentalsKnowledge Systems

Emergent Behaviors

Complex system behaviors that arise unexpectedly from simpler components interacting, not explicitly programmed

LLM FundamentalsSafety

End-to-End Eval

Evaluating complete AI system performance across entire workflows rather than isolated components

Evals

Enterprise Agents

AI agents deployed in organizations to autonomously execute business processes and complete multi-step tasks under organizational control.

Enterprise AIAgents

Enterprise AI Stack

The complete set of components an enterprise organization needs to build, deploy, and manage AI systems in production.

Enterprise AIArchitecture

Enterprise Framing

How to position and communicate AI capabilities to enterprise organizations by emphasizing control, governance, and business value.

Enterprise AI

Enterprise Governance

The organizational frameworks, policies, and oversight mechanisms that ensure AI systems are used appropriately and comply with requirements.

Enterprise AICompliance

Enterprise Memory & AI Systems

Persistent memory infrastructure that lets AI systems learn from past interactions and deliver personalized, context-aware experiences at scale.

Enterprise AIMemory & Context

Enterprise Metrics

The suite of quantitative measurements organizations use to assess whether AI systems are delivering business value and operating as intended.

Enterprise AIEvals

Enterprise Procurement

The organizational and contractual processes large companies use to evaluate, approve, and purchase AI systems and services.

Enterprise AI

Enterprise Workflows

Structured, automated processes within organizations that incorporate AI to automate decision-making, task routing, and multi-step operations.

Enterprise AIAgents

Episodic Memory (AI)

AI systems storing specific experiences and interactions in chronological context with sensory/contextual details

Memory & ContextAgents

Evals (Evaluation Systems)

Systematic testing frameworks that measure AI system quality across multiple dimensions like accuracy, safety, and efficiency

Evals

Event Loop (Agent Runtime)

The core execution mechanism that cycles through agent decision-making, tool execution, and state updates

AgentsInfrastructure

Explainability

Making AI decisions and outputs interpretable to humans, showing why the system generated specific responses

SafetyEnterprise AI

M

Maintenance

The ongoing operations and updates required to keep AI systems running effectively, including monitoring, bug fixes, updates, and performance optimization.

Enterprise AIInfrastructure

MCP (Model Context Protocol)

An open standard for exposing tools, data, and context to AI models, so any compliant model can discover and use any compliant integration.

InfrastructureAgents

Mechanistic Interpretability

Reverse-engineering the internal computations of a neural network into human-readable algorithms, features, and circuits

SafetyLLM Fundamentals

Memory & Optimization

Strategies for managing and persisting information about users, interactions, and context to improve AI performance while maintaining efficiency and privacy.

Memory & Context

Memory & Personalization

Tailoring AI responses and memory retrieval based on individual user preferences, history, and behavior patterns

Memory & Context

Memory Consolidation

Processing and integrating new experiences into organized long-term memory structures for persistent learning

Memory & Context

Model Routing

Systems that intelligently direct requests to different AI models based on criteria like cost, latency, accuracy, or specialization.

InfrastructureAgents

Multi-Agent Systems

Architectures where multiple AI agents work together, often with different roles or specializations, to solve complex problems collaboratively.

Agents

Multimodal AI

AI systems that can process multiple types of input (text, images, audio, video) and reason across them within a single model.

LLM Fundamentals

S

Safety Filters

Systems that detect and prevent AI models from producing harmful, unethical, or inappropriate content before it reaches users.

Safety

Sandboxing

Running agent-generated code and tool calls inside an isolated environment that has no more access than the specific task requires.

SafetyInfrastructure

Semantic Layer

A shared definition layer that turns raw tables into consistent business concepts, metrics, and relationships that anyone can query.

Data EngineeringKnowledge Systems

Semantic Search

Search that understands meaning rather than matching keywords, retrieving results based on conceptual similarity rather than exact word matches.

Knowledge Systems

Session Management

Systems that maintain and manage conversation context, user state, and history across multiple interactions with an AI system.

Memory & ContextInfrastructure

SKILL.md

The markdown file at the heart of an Agent Skill: YAML frontmatter the agent always sees, and a body it loads only when it decides the skill applies.

AgentsKnowledge Systems

Sparse Retrieval

Retrieval methods that use explicit keywords and term matching to find relevant documents, contrasting with semantic similarity-based approaches.

Knowledge Systems

State Management (Agent)

Systems that track and maintain the current status, progress, and internal variables of AI agents as they work through multi-step tasks.

AgentsMemory & Context

Structured Output

Constraining AI model outputs to specific, machine-parseable formats (JSON, XML, etc.) instead of free-form text.

LLM Fundamentals

System Prompt

Initial instructions provided to an AI model that define its role, behavior, constraints, and how it should respond to users.

LLM Fundamentals