Agents and automation

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 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 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.

Agent trajectory

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

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.

Chatbot

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

Control graph

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

Directed acyclic graph (DAG)

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

Dots

OpenAI's persistent agents that maintain context, use cloud computers and connected apps, and continue authorized work between conversations.

Durable execution

Persisting execution progress so unfinished work can resume after interruption, with explicit rules for replay and external side effects.

Execution graph

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

Grok Bot

SpaceXAI's persistent agent product, in which a user's Bots share a cloud computer and coordinate work across applications.

Handoff

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

Hermes Agent

Nous Research's open-source agent harness with persistent memory, reusable skills, tools, and a messaging gateway, able to run with different language models.

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.

Instinct

A hosted personal AI assistant developed by Spear Street Technology, founded by Noah Shinn, that users can text or call to delegate tasks across connected services.

IronClaw

NEAR AI's open-source personal-agent runtime, written in Rust, with persistent memory, tool capabilities, credential injection, and local or hosted deployment.

Model cascade

A sequence of model attempts that uses an acceptance or escalation rule to decide whether later stages must run.

Model routing

Selecting which separately deployed model will handle a request or step according to its inputs and an operating policy.

Multi-agent system

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

Muse

Meta's personal AI agent, which keeps context and works across connected applications from a dedicated cloud computer.

OpenClaw

An open-source agent platform for running a continuing assistant through messaging channels, with a Gateway, configurable models and tools, and a persistent workspace.

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.

State machine

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

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.

Workflow

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

Personal agent

An AI agent that serves an individual across tasks and sessions, using that person's context and preferences within delegated authority.

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.