Skip to content

Compare and learn

What these terms mean

Simple explanations for AI agent terms you keep seeing.

What is an agent executor? AI that completes tasks

An agent executor is a task tool where AI agents complete work in other apps, not only plan it. Definition, difference from a planner, examples.

Read guide

What is an approval gate in AI agents?

An approval gate is a checkpoint where an AI agent must get human approval before a sensitive action. Definition, examples, and how tools implement it.

Read guide

What is BYO agent? Bring your own AI agent or API keys

BYO agent means connecting your own AI agent or provider API keys to a task tool. What it changes for cost, privacy, and model choice.

Read guide

What is capture in AI task management?

Capture is turning meetings, voice notes, messages, and files into structured to-dos. Sources, accuracy, and what happens after capture.

Read guide

What is human in the loop for AI agents?

Human in the loop is an AI workflow where a person reviews or approves steps. How it differs from autonomous agents and where it belongs.

Read guide

What is MCP (Model Context Protocol)?

MCP is the open protocol that lets AI agents like Claude Code read and act on tools such as a to-do list. Definition and what a Doozy MCP server exposes.

Read guide