---
source: crewkit documentation
url: https://crewkit.io/docs/glossary.md
title: "Glossary"
description: "The words crewkit uses, each defined once, with where it appears on the dashboard and which page explains it. Where a thing has two names today, its entry gives both."
---


## Which part for which job

| The job | Use | Where on the dashboard |
|---|---|---|
| Make every developer run the same agent | [Agents](/docs/agents) | **Agents** in the sidebar, and a project's **Agents** tab |
| Give Claude Code a reusable how-to | [Skills](/docs/skills) | **Skills** in the sidebar, and a project's **Skills** tab |
| Hold the team's standards | [Playbooks](/docs/playbooks) and their conventions | **Playbooks** in the sidebar, and a project's **Playbooks** tab |
| Hold the project's documents | [Documents](/docs/documents) | A project's **Documents** tab |
| Ask someone outside the session a question | [Asks](/docs/asks) | **Asks** in the sidebar, and a project's **Asks** tab |
| Show someone a conversation | [Share links](/docs/sharing) | **Shares** in the sidebar |
| Message your other live sessions | [Session links](/docs/session-links) | **Settings → Session links** |
| Let teammates' sessions on one project message each other | [Session messaging](/docs/session-messaging) | A project's **Settings** page |
| Plan the work | [Blueprints](/docs/blueprints) | A project's **Blueprints** tab |

Each part is defined under [Terms](#terms) below.

## Terms

### Addressee

A member of your organization an Ask is addressed to, who answers it signed in.

**On the dashboard:** **Add members** in the Ask editor.
**More:** [Asks](/docs/asks)

### Agent

A prompt file for Claude Code that crewkit keeps and syncs to `.claude/agents/`, so every developer runs the same configuration. Agents are one kind of resource, with skills, commands and playbooks. Not the same as a [Team Agent](#team-agents) or an [agent role](#agent-role).

**On the dashboard:** **Agents** in the sidebar, and a project's **Agents** tab.
**More:** [Agents](/docs/agents)

### Agent role

A setting on each member that changes how agents work with them: coaching, collaborative or autonomous. It is separate from the member's permission level.

**On the dashboard:** your profile shows **Coaching Mode Enabled** when your role has coaching mode turned on.
**More:** [Team](/docs/team)

### Ask

A set of questions from one project to one [Audience](#audience), answered outside the session. A session or the dashboard drafts it, and a person publishes it.

**On the dashboard:** **Asks** in the sidebar, and a project's **Asks** tab.
**More:** [Asks](/docs/asks), [Asks privacy fact sheet](/docs/asks-privacy)

### Audience

The one group of people an Ask is written for, such as a client's product owners. A question for two Audiences is two Asks.

**On the dashboard:** on the Ask, in **Asks**.
**More:** [Asks privacy fact sheet](/docs/asks-privacy)

### Blueprint

A project's living plan: epics broken into tasks, with dependencies, acceptance criteria and links to the conversations that did the work.

**On the dashboard:** a project's **Blueprints** tab.
**More:** [Blueprints](/docs/blueprints)

### Capture mode

The organization setting that decides how much session content crewkit collects: `minimal`, `structured` or `full`. An organization admin sets it, for every member. An organization that never set it is on `structured`.

**On the dashboard:** **Settings → Organization → Privacy & Telemetry**.
**More:** [Capture modes](/docs/capture-modes)

### Command

A custom slash command for Claude Code, kept in `.claude/commands/`. Commands are one kind of resource.

**On the dashboard:** no sidebar entry of its own.
**More:** [Commands](/docs/commands)

### Confirmed results

A fixed copy, made when a person confirms an Ask, of its questions, its Decisions and the Responses that person was shown. Agents read only the latest copy. Respondents appear in it numbered, never named.

**On the dashboard:** a project's **Asks** tab.
**More:** [Asks](/docs/asks)

### Contradiction

A conflict crewkit found between a new document and an earlier one in the same project, by sending both to an Anthropic model. A person reviews each one.

**On the dashboard:** a project's **Contradictions** tab.
**More:** no page of its own yet; see [Documents](/docs/documents) for the documents it compares.

### Conversation and session

A **conversation** is the stored record of one piece of work with Claude Code; a **session** is the running Claude Code process that produces it. The dashboard lists conversations inside a project. The CLI command and the API path that handle the record are named `sessions`, for the process that starts it. A conversation holds what the [capture mode](/docs/capture-modes) collects, and members read it as described under [Viewer](#viewer).

**On the dashboard:** a project's **Conversations** page.
**More:** [Dashboard](/docs/dashboard-overview), [Sessions API](/docs/api-sessions)

### Data plane and resident

A data plane is a crewkit service an organization runs in its own cloud to hold its session content. An organization that uses one is **resident**: the CLI sends transcript and hook-event content to the data plane. crewkit stores no transcript text, first prompt or summary for it; it receives reduced hook events and each session's metrics: who ran it, the project, when, tokens and cost.

**On the dashboard:** **Settings → Organization**, the **Data Plane** card.
**More:** [Capture modes](/docs/capture-modes)

### Decision

The answer a person records for one question of an Ask, after reading its Responses, with the reason. A majority of Responses never makes a Decision on its own.

**On the dashboard:** on the Ask, in a project's **Asks** tab.
**More:** [Asks](/docs/asks)

### Documents

A project's memory: uploaded files, Google Drive imports, captured email and Slack messages, and past sessions, all searchable. Captured email and Slack messages can be found by search, by members and by agents, as soon as they arrive; crewkit adds them to a session's context on its own only after a person confirms them. A document's text is sent to Voyage AI to make it searchable and to Anthropic for analysis, except where your organization's data settings bar it. The dashboard says **Documents**; the API calls them Artifacts.

**On the dashboard:** a project's **Documents** tab.
**More:** [Documents](/docs/documents)

### Feedback

Two different things. **Feedback** is the panel a team adds to its own app, so the people using that app can send the team a message. A report also carries the name and email they typed, the page, the browser and an optional screenshot. A report nobody confirms is deleted 30 days after it arrives; a confirmed one is kept 180 days by default. `crewkit feedback "message"` is a CLI command that sends your own message about crewkit to the crewkit team.

**On the dashboard:** a project's **Feedback** tab, and pending reports in the **Inbox**.
**More:** [Feedback](/docs/feedback), [CLI](/docs/cli)

### Inbox

The page where content waits for a person to confirm it: Asks with Responses not yet confirmed, inbound messages crewkit could not file to a project, code-host items to confirm, email and Slack documents held until a person confirms them for agents, and pending Feedback. Email and Slack messages are searchable while they wait.

**On the dashboard:** **Inbox** in the sidebar.
**More:** [Feedback](/docs/feedback), [Agent identities](/docs/agent-identities)

### Lesson

A short rule a person on your team wrote or approved after the same evidence came up for two or more people on a project. Accepted Lessons are added to later sessions on that project. Lessons are off until crewkit has enabled them for your organization and an organization admin has switched them on.

**On the dashboard:** a project's **Lessons** tab.
**More:** [Lessons](/docs/lessons)

### Playbook and convention

A playbook is a collection of conventions: the team's standards, such as which test framework to use. Your organization subscribes to playbooks and assigns them to projects.

**On the dashboard:** **Playbooks** in the sidebar, and a project's **Playbooks** tab. **Analytics → Conventions** shows when sessions overrode a convention.
**More:** [Playbooks](/docs/playbooks)

### Project and Workspace

A project is where crewkit keeps a team's context, conversations and settings. A workspace is a kind of project that runs work across several repository projects.

**On the dashboard:** **Projects** in the sidebar. A new project is a repository project or a **Workspace**.
**More:** [Workspaces](/docs/workspaces)

### Respondent

A person who answers an Ask through its link, signed in to crewkit or not.

**On the dashboard:** numbered in an Ask's Confirmed results.
**More:** [Asks privacy fact sheet](/docs/asks-privacy)

### Response

One Respondent's answers to one version of an Ask. Changing an answer adds a new version of the Response and keeps the earlier one.

**On the dashboard:** on the Ask. The **Inbox** lists Asks with Responses not yet confirmed.
**More:** [Asks](/docs/asks)

### Rule

A Markdown file in `.claude/rules/` that Claude Code loads by file path. It is a Claude Code feature: crewkit does not store or serve rules.

**On the dashboard:** none.
**More:** [Rules](/docs/rules)

### Sensitive session

A session started with `crewkit --sensitive`. In an organization crewkit hosts, its transcript and hook events are still sent and stored under the capture mode, but only the person who ran it can find or open it, not a manager or an admin. It is left out of session analysis, project search, correction detection, convention override resolution and Lessons, and only that person can share it.

**On the dashboard:** none; you choose it when you start the session.
**More:** [CLI](/docs/cli), [Capture modes](/docs/capture-modes)

### Session link

Messaging between your Claude Code sessions that are already running, on any machine. Only the messages each session sends cross; no conversation, context or transcript is shared. Each message is kept in both conversations' transcripts, and is readable by whoever can read those conversations.

**On the dashboard:** **Settings → Session links**.
**More:** [Session links](/docs/session-links)

### Session messaging

A project setting that lets the live sessions of people on that project message each other with no pairing step. It is off by default.

**On the dashboard:** the **Session messaging** card on a project's **Settings** page.
**More:** [Session messaging](/docs/session-messaging)

### Share link

A link that shows one conversation at the level you chose: to signed-in members of your organization or, when an admin makes it Public, to anyone holding the link, with no account. Signed-in members can add annotations to it. It expires when you set, or never.

**On the dashboard:** **Shares** in the sidebar.
**More:** [Session sharing](/docs/sharing)

### Skill

A focused, reusable how-to that Claude Code can call for one kind of task, such as reviewing a pull request. Skills are one kind of resource.

**On the dashboard:** **Skills** in the sidebar (Catalog, Yours, Builder), and a project's **Skills** tab.
**More:** [Skills](/docs/skills)

### Team Agents

A project's agent teammates, each with its own email address and an optional Slack handle. The dashboard says **Team Agents**; the docs page calls them agent identities. Not the same as an [Agent](#agent).

**On the dashboard:** a project's **Team Agents** tab.
**More:** [Agent identities](/docs/agent-identities)

### Viewer

The read-only permission level. A Viewer reads analytics, documents, Asks and other members' conversations, transcripts included. It cannot read conversations in Restricted or Private repositories, or sensitive sessions. The content of a session that took in a meeting transcript is read by managers and above. What a Viewer costs is on the [pricing page](/pricing).

**On the dashboard:** **Team** in the sidebar.
**More:** [Team](/docs/team)
