Agents and automation

Agent loop

The repeated cycle in which an agent observes state, selects an action, invokes a tool or model, receives feedback, updates state, and decides whether to continue.

Agent trajectory

The ordered record of states, model outputs, actions, tool results, and transitions produced during an agent run.

Chatbot

A conversational software interface that accepts natural-language input and returns responses, whether powered by rules, retrieval, generative models, or combinations of them.

Directed acyclic graph (DAG)

A directed graph with no path that returns to an earlier node.

State machine

A model of a system as explicit states and permitted transitions triggered by events or conditions.

Workflow

A defined sequence or graph of activities, decisions, states, and transitions used to achieve an outcome.

AI agent

A software system in which a model interprets a goal or input, decides among actions, uses tools or other capabilities, observes results, and continues until completion, handoff, or termination.

Agent harness

The software layer that surrounds a model with instructions, context assembly, tools, state, permissions, control flow, budgets, verification, observability, and recovery.

Agent scaffold

A task-specific arrangement of prompts, tools, control logic, and feedback wrapped around a model to improve performance.

Agent skill

A versioned package of instructions, procedures, examples, and sometimes code or resources that teaches an agent how to perform a repeatable class of work.

Agentic

Describing a system that can choose and sequence actions toward a goal with some runtime discretion rather than only produce a single predetermined response.

Control graph

A directed representation of the steps an agent system may execute and the conditions that select what runs next.

Execution graph

A run-oriented graph of executable steps and the control or data dependencies connecting them.

Handoff

A transfer of active responsibility, context, and next-action authority from one agent or person to another.

Human in the loop (HITL)

An operating pattern in which a human participates directly in the decision or execution path before work can continue.

Human on the loop (HOTL)

An operating pattern in which a system acts while a human supervises, receives evidence or alerts, and can intervene or stop it.

Human out of the loop

An operating condition in which a system completes a scoped activity without routine human participation in its action path.

Multi-agent system

A system in which multiple agents communicate, specialize, coordinate, compete, or verify one another to accomplish work.

Orchestration

Coordinating tasks, agents, tools, state, dependencies, budgets, failures, and lifecycle across a workflow.

Orchestrator

The component or role that admits work, assigns it, coordinates dependencies and concurrency, tracks state, handles retries, and determines handoffs or completion.

Subagent

An agent invoked by another agent or orchestrator to perform a bounded portion of a larger task.

Task decomposition

Breaking an objective into smaller units with explicit dependencies, interfaces, acceptance criteria, and ownership.

Autonomy

The degree to which a system can select and execute actions without case-by-case human direction or approval.

Graph engineering

Designing an agent system as explicit nodes, state, and transitions so deterministic control and model judgment have visible boundaries.

Loop engineering

Designing the feedback cycles around an agent so action, verification, operational triggers, and system improvement have explicit state, evidence, limits, and stopping conditions.