AI Glossary
367+ production AI terms, organized by chapter.
Search across every term, or browse by chapter — from agentic AI and RAG to LLMOps, evaluation, and MCP.
60 results
AI AgentAn AI agent is a system that pursues a goal by repeatedly deciding on actions, executing them through tools or the environment, and observing the results to…Agent LoopThe agent loop is the repeating cycle an agent runs: it reads the current context, decides on the next action (often a tool call or a message), executes that…Tool-Calling AgentA tool-calling agent is an AI agent that extends a language model's capabilities by invoking external functions — such as web search, code execution, or…ReAct AgentA ReAct agent interleaves explicit reasoning traces with concrete actions in a single generation pass. The model writes a thought explaining its current…Autonomy LevelAutonomy level describes how much independent decision-making authority an agent has before a human must review or approve its actions. A fully automated…Agent RuntimeThe agent runtime is the infrastructure layer that hosts and drives the agent loop. It manages prompt assembly, tool dispatch, state persistence, retry logic,…Human-in-the-LoopHuman-in-the-loop refers to design patterns where a human operator is inserted into an otherwise automated agent pipeline at defined checkpoints. The human…Agent TrajectoryAn agent trajectory is the complete sequence of states, actions, and observations that an agent produces while working toward a goal. Capturing trajectories…Action SpaceThe action space is the set of all actions an agent is permitted to take at any given step. It typically includes tool calls, sub-agent invocations, and…Agent EnvironmentThe agent environment encompasses everything external to the model that the agent can observe and affect. It includes file systems, APIs, databases, web…Agent StateAgent state is the information the agent carries across loop iterations to maintain continuity. It can include the conversation history, scratchpad notes,…Deterministic vs Non-Deterministic Agent BehaviorA deterministic agent produces the same sequence of actions given the same inputs and state, making it reproducible and easier to test. A non-deterministic…Agent EvaluationAgent evaluation measures whether an agent reliably achieves its goals across a representative set of tasks and edge cases. Unlike single-call evals, agent…Agent PersonaAn agent persona is the identity, tone, and behavioral constraints assigned to an agent through its system prompt. Personas establish how the agent introduces…Step BudgetA step budget is a hard upper limit on the number of loop iterations or tool calls an agent is allowed to make during a single task run. It prevents runaway…Agentic WorkflowAn agentic workflow is a pipeline in which one or more AI agents, rather than hard-coded logic, drive the sequencing and execution of steps toward a goal. The…Orchestration vs Single-AgentA single-agent architecture uses one model instance to reason, plan, and act across all subtasks. An orchestrated architecture uses a coordinating agent to…Agent ObservabilityAgent observability refers to the tooling and practices that give operators visibility into an agent's runtime behavior — including which tools were called,…Guardrailed AgentA guardrailed agent operates under a set of enforced constraints that prevent it from taking harmful, out-of-scope, or policy-violating actions. Guardrails…Agent MemoryAgent memory covers the mechanisms by which an agent retains and retrieves information across turns and sessions. In-context memory lives in the active prompt…Agent HandoffAn agent handoff is the transfer of task control from one agent to another in a multi-agent pipeline. The handing-off agent packages the current task context,…Agentic RAGAgentic RAG extends basic retrieval-augmented generation by giving an agent control over when, what, and how to retrieve information. Rather than a single…Least-Privilege AgentA least-privilege agent is granted only the minimum tool permissions and data access required for its current task, and nothing more. By narrowing the action…Dry-Run ModeDry-run mode lets an agent plan and log the actions it intends to take while suppressing execution of any side-effecting tools. Operators can review the…Agent SandboxAn agent sandbox is an isolated execution environment that confines what an agent's tools can touch — restricting filesystem, network, and secret access to an…Self-Healing AgentA self-healing agent detects when a tool call or step has failed and attempts recovery on its own — retrying with adjusted arguments, choosing an alternative…PlanningPlanning is the process by which an agent reasons about a sequence of steps needed to achieve a goal before committing to action. A planner considers…Task DecompositionTask decomposition breaks a high-level objective into smaller, independently executable subtasks. By reducing scope at each step, the agent can tackle…Chain-of-ThoughtChain-of-thought prompting elicits intermediate reasoning steps from a language model before it produces a final answer. By generating a verbal walkthrough of…Tree of ThoughtsTree of Thoughts treats problem solving as a search over a tree where each node is a partial reasoning state. Rather than following a single linear chain of…ReAct ReasoningReAct reasoning is a prompting strategy that interleaves natural-language thought traces with discrete action commands in the same generation. The model…ReflectionReflection is a deliberate self-evaluation step in which an agent reviews its own outputs, reasoning traces, or past actions and identifies mistakes, gaps, or…Self-CritiqueSelf-critique is the technique of prompting a model to act as its own critic: after producing an initial output or plan, the model is asked to identify flaws,…Plan-and-ExecutePlan-and-execute is an agent architecture that separates planning from execution into distinct phases. A planner model or prompt first produces a structured…GoalA goal is the desired end state or outcome that an agent is tasked with achieving. Goals can be specified as success conditions, natural-language…SubgoalA subgoal is an intermediate milestone that an agent must achieve as part of reaching a larger goal. Decomposing a complex objective into subgoals gives the…BacktrackingBacktracking is the ability of an agent to abandon an unsuccessful reasoning path or action sequence and return to an earlier decision point to try an…Hierarchical PlanningHierarchical planning organizes a task as nested layers of abstraction: high-level plans specify major phases of work, while lower-level plans spell out…ReplanningReplanning occurs when an agent revises its plan in response to unexpected observations, tool failures, or changed conditions discovered during execution.…ScratchpadA scratchpad is a designated section of the model's generation — or an external text buffer — where the agent can write intermediate calculations, notes, or…DeliberationDeliberation is the process of spending additional compute — through extra reasoning steps, candidate generation, or evaluation passes — to arrive at a…HeuristicIn the context of agent planning, a heuristic is a rule of thumb or scoring function that estimates the promise of a partial plan or reasoning path without…Least-to-Most PromptingLeast-to-most prompting is a technique that teaches a model to first solve the easiest subproblem, use that solution to tackle the next slightly harder one,…Self-ConsistencySelf-consistency is a decoding strategy that samples multiple independent reasoning paths for the same question and aggregates the final answers — typically…Plan VerificationPlan verification is the step of checking a generated plan for correctness, feasibility, and completeness before execution begins. Verification can be…Task GraphA task graph is a directed acyclic graph in which nodes represent individual subtasks and edges represent dependency relationships between them. An agent or…Means-Ends AnalysisMeans-ends analysis is a planning strategy that repeatedly compares the current state with the goal state, identifies the largest difference between them, and…Plan MonitoringPlan monitoring is the continuous check of whether execution is still tracking the intended plan and whether the plan's assumptions still hold. When an…Goal ConditioningGoal conditioning is the practice of keeping an explicit statement of the objective present in the agent's context so that every reasoning and action step is…Cost-Aware PlanningCost-aware planning weighs the expected token, latency, and tool-invocation cost of candidate plans, not just their likelihood of success. An agent may prefer…Function CallingFunction calling is a model capability that allows a language model to emit a structured request to invoke a named function with typed arguments, rather than…Tool SchemaA tool schema is the formal description of a tool that the language model receives at inference time: it includes the tool's name, a natural-language…Tool RouterA tool router is the logic — implemented in prompt, code, or a dedicated model — that selects which tool to invoke given the current state of the agent's…Structured OutputStructured output is the practice of constraining a model's generation to conform to a defined schema — such as JSON, XML, or a typed Pydantic model — rather…JSON ModeJSON mode is a model inference setting that guarantees the output is syntactically valid JSON. It does not guarantee semantic correctness or schema…Parallel Tool CallsParallel tool calls allow a model to emit multiple tool invocation requests in a single generation step, which the runtime then executes concurrently before…Tool ResultA tool result is the data returned by a tool execution that is fed back into the model's context as an observation. The model then incorporates this…Argument ValidationArgument validation is the process of checking that the arguments a model supplies in a tool call conform to the tool's schema — verifying required fields are…API ToolAn API tool is a tool that wraps an external HTTP API, exposing one or more endpoints as callable functions within an agent's action space. The tool handles…Code Execution ToolA code execution tool allows an agent to run programs — typically Python or shell scripts — in a sandboxed environment and receive the output as a tool…
Browse by chapter
Agentic AI Foundations & Architectures
Core building blocks of autonomous AI agents — agent loops, roles, and system shapes.
26 terms
Agent Planning & Reasoning
How agents decompose goals, plan steps, and reason toward outcomes.
24 terms
Tool Use & Function Calling
Connecting models to tools, APIs, and structured function calls.
24 terms
Memory, Context & State
Short- and long-term memory, context windows, and state management for agents.
20 terms
Multi-Agent Systems & Orchestration
Coordinating multiple agents — roles, communication, and orchestration patterns.
20 terms
RAG & Grounded Generation
Retrieval-augmented generation — chunking, retrieval, reranking, and grounded answers.
29 terms
Vector Databases & Retrieval
Embeddings, vector indexes, similarity search, and hybrid retrieval.
25 terms
MCP & Integration
Model Context Protocol and patterns for tool-connected, integrated AI apps.
21 terms
MLOps, LLMOps & Observability
Deploying, monitoring, evaluating, and improving models in production.
30 terms
Evaluation, Guardrails & Safety
Measuring quality, adding guardrails, and testing for regressions and failures.
30 terms
Prompt Engineering
Designing reliable prompts, templates, and reusable prompting patterns.
24 terms
Fine-Tuning & Alignment
Adapting models with fine-tuning, preference optimization, and alignment.
23 terms
LLM Core & Architecture
Transformer internals, attention, tokenization, and decoding.
24 terms
Classical AI, NLP & Linguistics
Foundational NLP and machine-learning concepts that underpin modern systems.
22 terms
AI Safety, Ethics & Risk
Bias, robustness, misuse, and responsible-AI concepts.
25 terms