How d5s fits together

d5s separates ownership, reusable context, work behavior, and individual runs. A project holds approved context once, so chats, agents, and automations can all use it.

The hierarchy

1. An organization owns the broader member, group, billing, usage, audit, model availability, and residency boundary. It can contain multiple workspaces. Its Owners and Admins can compare usage across them, and they are automatically Admins of every workspace in it. Opening one usage row requires access to its conversation. Its region is selected when it is created; one user account can belong to organizations in several regions. Owners and Admins can change its display name while its URL slug and region remain stable.
2. A workspace is one day-to-day operating area. It contains projects and its own skill, connector, and API-key catalogs. Models follow the organization policy. Organization managers and workspace administrators can invite people into that exact workspace without opening the organization's other workspaces. If a team uses seats on joining, an organization Owner or Admin must authorize any new seat before the invitation is sent. Its display name can change while its URL slug remains stable.
3. A project owns the reusable context and sharing policy for a body of work.
4. A chat, agent, automation, or dashboard determines how work is initiated and presented.

Start a chat, automation, or dashboard without setting up a named project first. Choose a project when people or recurring work should share its instructions, files, and access. Use Save as project to make the context behind an ongoing chat visible in Projects. Manage an agent's context through that agent's settings.

How the work modes keep history

• A chat keeps its conversation across turns.
• An agent keeps a continuing conversation for messages, connected channels, and wakeups.
• An automation shows each occurrence in its run history.
• A dashboard keeps build and refresh history alongside published versions.

Context and capabilities

Context is what the agent can know: standing instructions, conversation history, project memory, and files. Capabilities are what it can do: follow a skill, call an activated connector, search the web, execute code, or create an artifact.

Connecting GitHub makes the account available in the workspace. Check that it is enabled for the intended project, then review any Ask approval card before the agent takes the action.

Preview Word documents

A Word page preview keeps tables and saved form answers together. Form checkboxes show the saved selection and are read-only in the preview. If the page preview is unavailable, d5s shows a simplified document preview. Use Download to open the original file in Word when you need to edit answers or compare formatting.

Word documents with tracked changes

Give an agent a Word file and ask for changes "as track changes". The agent returns a new copy with real Word revisions and comments under its own name, so the reviewer sees insertions, deletions, and reasons in the document preview and can accept or reject each one in Word. Revisions and comments that were already in the file stay untouched. The preview's Markup and Final views switch between the redline and the clean result.

Execution remains visible

A message or trigger starts work in its conversation. You can review progress, tool activity, usage, and the final result. The conversation and its project context remain available after the work ends.

This model lets you stop a run without deleting its conversation, branch a completed response into a new chat, inspect an automation's past executions, or restore an earlier dashboard version without losing the resource that produced it.