Glossary
This glossary defines every term Endue uses. Each entry links to the page where the concept is covered properly. A term that appears in the product but not on this page is a documentation bug — please tell us.
A durable identity that does work on your behalf, with its own handle, profile, character, and system prompt. Unlike a chat window you open and discard, an agent persists: it keeps its abilities, its memory, and its history. An agent can only reach what you have bound to it.
Learn more: Core concepts
Agent Builder
Section titled “Agent Builder”The part of the web app where you create and tune agents — identity, system prompt, model, and the skills and connections bound to them.
The name is Agent Builder. “Studio” is not a product name and does not appear in the interface.
Learn more: Agent Builder
Approval
Section titled “Approval”A pause in a run where Endue asks you to confirm before the agent takes an action you cannot take back. Two categories always trigger it: outbound actions that leave your account and reach another person, and destructive actions that delete or overwrite data.
You see the exact action with the exact arguments before deciding. This gate is not configurable. In a routine or any other run nobody is watching, the action is refused rather than left waiting.
Learn more: Approvals · Core concepts
Artifact
Section titled “Artifact”A document, report, diagram, or dataset an agent produced, stored on its own page rather than buried in a conversation. Artifacts are private to you by default and can be shared with a link that grants access to that one artifact and nothing else.
Learn more: Artifacts
Binding
Section titled “Binding”The link between an agent and a capability it is allowed to use. Connections and skills are bound to specific agents — holding a connection in your account does not grant it to every agent you own.
Binding is what keeps an agent’s reach predictable. An agent with three tools behaves more consistently than one with twenty.
Learn more: Connectors overview
“Bring your own key.” Using your own model-provider credentials for an agent’s model calls instead of Endue’s.
Learn more: Bring your own key
Channel
Section titled “Channel”A pairing that lets people reach an agent from outside Endue — a Discord server or a Slack workspace. The opposite direction from a connector, which lets an agent reach a service.
Learn more: Channels
Character
Section titled “Character”The disposition that shapes an agent’s tone and style. Separate from the system prompt, which defines the job rather than the manner.
Connection
Section titled “Connection”An authorized link between your Endue account and an external service — your Gmail account, your Slack workspace, your Notion. A connection is tied to one account at the provider and can be revoked from either side at any time.
Connecting a service is not the same as granting it: a connection must be bound to an agent before that agent can use it.
Learn more: Connectors overview
Connector
Section titled “Connector”The integration that makes a service connectable. Gmail is a connector; your authorized Gmail account is a connection. Endue ships connectors for more than thirty services.
Learn more: Available connectors
Conversation
Section titled “Conversation”A continuous, persistent thread with an agent. It holds the message history the agent reads for context and survives closing the app. Conversations can be grouped into a project when several of them concern the same body of work.
Learn more: Conversations
Handle
Section titled “Handle”The short name you use to address an agent. Chosen when the agent is created and stable afterwards.
Where notifications land: a run finished, a routine completed or failed, something is waiting on your decision. It tells you what happened; you act on it in the conversation it points to.
Learn more: Notifications and inbox
Memory
Section titled “Memory”What an agent retains across conversations — facts about you, your preferences, how you like work done. The agent decides what is worth keeping and recalls it when relevant, so memory is selected rather than dumped into every run.
Memory is inspectable and editable: you can see what an agent stored and delete anything that should not have been kept.
Learn more: Memory
Project
Section titled “Project”A grouping of conversations, artifacts, and routines that belong to the same body of work. An agent working inside a project sees the project’s context, which is the cheapest way to stop re-explaining background in every conversation.
Learn more: Projects
Reasoning effort
Section titled “Reasoning effort”How much thinking a model does before it answers. Higher effort costs more tokens and takes longer, and pays off on multi-step work where an early wrong turn wastes the rest of the run. Available on models that support it.
Learn more: Choosing a model
Revision
Section titled “Revision”A saved version of an agent’s system prompt. Prompts are versioned so a change can be reviewed and rolled back — which is what makes prompt iteration safe rather than a gamble.
Learn more: System prompt and revisions
Routine
Section titled “Routine”A task an agent performs on a schedule, running whether or not you have Endue open. What a routine produces waits for you in your workspace. If it needs a decision it asks, and an approval it cannot get is refused rather than left hanging.
Learn more: Routines
One turn of an agent working: read the context, decide, call a tool, read the result, repeat until done or until it needs you. Runs execute on Endue’s servers, so closing the app does not stop the work.
Learn more: Runs · How Endue works
A packaged, repeatable job — a procedure, a checklist, a set of commands — that can be bound to an agent so you do not have to re-explain it. An agent can also request a skill it has not been given, pausing mid-run for you to grant or decline.
Learn more: Skills
A shared workspace where a team uses the same agents and sees the work they produce.
Steering
Section titled “Steering”Sending a correction to an agent while a run is still in progress. The agent picks it up on its next step, so a correction costs one step rather than the whole run.
Learn more: Steering a run
Surface
Section titled “Surface”One of the places you can use Endue: the web app, the desktop app, mobile, or the command line. All surfaces reach the same agents, conversations, and history — you can start on one and continue on another.
Learn more: Surfaces
System prompt
Section titled “System prompt”The standing instructions an agent reads before every conversation: what it does, what it must never do, and what a good result looks like. Kept under revision history.
Learn more: System prompt and revisions
A single capability an agent can invoke during a run — read a file, search email, create a calendar event, write an artifact, recall a memory. Tools are what make an agent able to act rather than only advise.
Some tools are built in and always present. Others appear only when a connection or skill is bound to the agent.
Learn more: Built-in tools · Core concepts
Tool call
Section titled “Tool call”One invocation of a tool within a run, visible to you as it happens, along with what it returned.
Retired terms
Section titled “Retired terms”These appear in older material. Use the current name.
| Old term | Now called | Notes |
|---|---|---|
| Studio | Agent Builder | Never a product name; do not reintroduce it |
| Character build, quest, party | — | The RPG framing is retired from product copy |