Browse this section
Getting started

Core concepts

The objects that make up the platform and how they relate.

Workspace

A workspace belongs to one company. It holds users, roles, knowledge bases, agents, API keys and billing. Enterprise customers can have several workspaces (for example per subsidiary) under one organisation.

Users and roles

RoleCan
MemberAsk questions in channels and the web app; see their own conversations; trigger agents they've been granted
EditorEverything a member can, plus create and edit agents and knowledge bases they own
AdminManage users, roles, sources, apps, API keys and billing; see all run traces and audit logs
OwnerAdmin plus contract, data deletion and workspace transfer

Knowledge base

A named, permission-aware index of content from one or more sources. Access to a knowledge base is granted to users, channels and agents. A question is answered from the knowledge bases the asker can access, filtered further by the asker's permissions in each source.

Source

A connection to a system (Google Drive folder, SharePoint site, Notion workspace, Zendesk account…). A source belongs to exactly one knowledge base and syncs content and permissions on a schedule or via change notifications.

Document and chunk

A document is one item from a source (a file, a page, a ticket, a Slack thread). Documents are split into chunks for retrieval. Citations point to a chunk and, where the source supports it, to the exact location inside the document.

Query

One question to the Knowledge Search Agent, from any channel or the API. A query produces an answer, citations and a confidence score, and is logged.

Conversation

A thread of queries and answers that share context — a Slack thread, a Teams chat, a web-app conversation, or an API conversation you create.

Agent

A configured worker with a job (instructions), knowledge bases it may read, tools with scopes, guardrails, triggers and optionally an evaluation set. Agents are versioned; a version is promoted from test to production.

Tool

A capability an agent can use: read a mailbox, write a row, post a purchase invoice, call an HTTP endpoint. Tools come from integrations and have separate read and write scopes.

Run

One execution of an agent, from trigger to completion. A run has a trace — every retrieval, tool call, decision and approval — and a status: queued, running, waiting_approval, succeeded, handed_off, failed, cancelled.

Approval

A pause in a run where a policy requires a person to allow a tool call. Approvals are answered in Slack, Teams, the web app or via API.

Trigger

What starts a run: a schedule, an event from a connected system, a webhook, a mention in chat, or a manual start.

Audit log

An immutable record of security-relevant events in the workspace: sign-ins, permission changes, source connections, API key actions, agent promotions, emergency stops. Exportable to your SIEM.