Administer d5s

Administer d5s by separating who may enter the workspace, what context they may access, and what actions their agents may perform. A controlled rollout can begin with one project and one connector rather than configuring the entire organization at once.

1. Establish membership and ownership

Confirm the organization owner and workspace owner before inviting a broader group. Organization ownership carries billing and destructive powers that ordinary workspace administration does not.

An organization Owner or Admin can open Settings, choose the organization in the selector under Organization, and select Workspaces to create or govern its workspaces. The same person can also create one without leaving their current page: the workspace switcher lists the current organization's workspaces first, with a Create workspace plus button in its header for that organization. A single Switch organization row opens the list of other organizations; each is one selection and opens the workspace you last used there, and an organization with no workspace yet shows Create workspace. The create controls appear only for the organizations you may create in, so the switcher shows the same Owner or Admin gate the Workspaces page applies. Other regions appear at the foot of the menu in a compact Other regions section. Available destinations are navigation links, not organization or membership claims, and ask for a fresh account choice; a destination that is not available yet says Coming soon and has no link. Profile and Preferences stay under You. Open Workspaces, choose a workspace, then select an available tab: General, Members, Browser, Network, or Developers. On a narrow screen, use the Settings index and the workspace and section selectors. Developers contains API keys; credentials remain in Connectors.

To change the organization display name, select General in that Organization group and edit Name. The new name saves when you press Enter or leave the field. The slug is read-only: a new display name updates organization labels throughout d5s without changing existing links, workspace access, billing ownership, or existing audit records. The audit log adds an organization rename event.

To add the organization logo, select Upload in the Logo row of the same page and choose a PNG, JPEG, WebP, or SVG image of up to 5 MB. d5s fits it into a small square without cropping and saves it at once; it replaces the letter tile in the sidebar and the workspace switcher for everyone in the organization. Use Replace or Remove to change it later. Each change adds a logo event to the audit log. A personal organization has no logo row: it shows its owner's avatar.

To require no-training models for every member, select Privacy in the same Organization group and enable Require no-training routes for everyone. The setting applies to all work in the organization, interactive and unattended. Muse Spark 1.2 Contributor and Muse Spark 1.3 Contributor are no longer available, even when no-training routing is off. Turning the requirement off does not weaken a member who enabled their own setting under Preferences → Privacy. Both settings are off by default, and every change is audited.

The workspace creator becomes its sole Owner. Add users or groups explicitly on that workspace's Settings → Workspaces → workspace name → Members tab. Plain organization membership does not grant access to workspace content. Active organization Owners and Admins are the exception: they are automatically Admins of every workspace in the organization, including new ones. Their access shows as Organization admin and follows their organization role. To hand a workspace to someone else, an organization Owner or Admin uses Workspaces → workspace name → General → Danger zone → Transfer ownership. The new workspace starts with its own projects, skills, connector credentials, and API keys; secrets and project content are not copied from an existing workspace. Models follow the organization's shared policy, not a per-workspace setting.

For a non-personal workspace, its Owner or Admin can use Invite people in the workspace sidebar or Settings → People when Settings was opened from that workspace. Organization Owners and Admins can send the same workspace-scoped invitation. Choose Member or Admin for that workspace; accepting adds a new collaborator to the organization only as a plain member and preserves an existing organization role. Invite each workspace separately. The personal workspace is private and never accepts invitations; its Invite people control instead opens Create a workspace to invite people, creates the named workspace in your personal organization, and opens People with the new workspace selected for the invitation. For a team that purchases seats upfront, raise the seat count before inviting past the subscription's capacity. If your team uses seats on joining, select Review invite first. An organization Owner or Admin reviews the joining charge and individual seat's monthly price, then selects Authorize seat and invite or, when offered, Reserve free seat and invite. Pending invitations carry no charge. Acceptance adds any needed standard seat after payment or the displayed waiver and opens the invited workspace. Existing team members need no extra seat. Expired terms require a new review and authorization; see Plans and credits for quote and offer deadlines. See Sharing and permissions.

A workspace Owner or Admin can change its display name from Settings → Workspaces → workspace name → General → Workspace details. Type the new name and press Enter or leave the field to save it. Renaming is an ordinary setting, not a Danger zone action. It updates the name shown in d5s without changing the workspace slug or any existing links. Organization Owners and Admins are Admins of every workspace, so they can rename it there too. The organization's Workspaces page has no rename control.

Delete a workspace safely

Open Settings → Workspaces → workspace name → General → Danger zone and select Delete…. A workspace Admin who is not the Owner sees Review deletion. The dialog lists content and connections that d5s will remove. You do not need to delete them first.

Only the workspace Owner can continue. Read the impact, select the acknowledgment, request the six-digit email code, enter the exact case-sensitive workspace name, and select Schedule deletion. The workspace stays available for 48 hours. Content added during that period is included. Workspace Owners and Admins receive a notice and can cancel from the same dialog before cleanup starts.

At the deadline, d5s stops new work, removes the workspace and its content, and sends a completion email when cleanup finishes. Personal workspaces cannot be deleted. If ownership changes or the requester becomes inactive before the deadline, deletion is cancelled. If cleanup needs attention, the dialog shows that status; contact support.

Assign the narrowest current workspace role that lets each person do their job:

Workspace roles

Role	Main access
Owner	Full workspace control, including members, settings, capabilities, and deletion.
Admin	Manage workspace members, settings, skills, and connectors.
Member	Create and use workspace resources.
Viewer	Read-only workspace access.

Use project sharing for access to a particular body of work instead of elevating the person's workspace role.

2. Choose a pilot project

Create one listed project with a clear owner, representative files, and a small group of participants. Decide whether it is available to everyone in the workspace or restricted through explicit people and group grants.

Keep project instructions short and operational: identify the purpose, approved evidence, review expectations, and actions that always require a person.

Put rules that apply to every project, such as language and tone, in the workspace instructions under Workspaces → workspace name → General → Instructions.

3. Connect capabilities deliberately

Select a provider in Connectors to review its detail page before connecting an account. After setup, choose Manage permissions to review available tools, the Approval choice that also covers future tools, and individual choices.

Open Connectors and add only credentials appropriate for general use in this workspace. Prefer an external account with the narrowest useful provider permissions. A connected credential attaches to existing and future projects, chats, automations, dashboards, and agents by default; remove it from each project or agent that should not use it. Conversationally created agents use only their draft-reviewed connections and do not inherit future workspace credentials; see Create your first agent.

After activation, review the controls shown for that credential. Known MCP reads normally allow while writes and unknown actions ask. Newly discovered operations absent from the reviewed inventory ask unless an explicit tool policy applies. API operation controls are not available for every connector, so do not rely on an approval boundary unless the credential displays and enforces it.

4. Prove one workflow

Ask a member to complete the workflow interactively and review its sources, tool activity, approvals, generated files, and usage. Only then turn the pattern into an agent or automation.

For autonomous work, start with a budget or conservative schedule and a clear destination. Keep a named person responsible for reviewing failures and external actions.

5. Review the boundary regularly

For subscriptions in euro, Checkout asks the buyer to confirm a full billing address. A business buyer can also provide its legal name and a supported tax ID, and Stripe records corrected billing details for later invoices. Checkout itemises the resulting tax before payment, including supported reverse-charge treatment.

Remove unused project grants, archive credentials that should no longer be activated, and investigate repeated approval or authorization failures. On the Connectors page, select an installed provider to review who set each credential up and when, then reassign or archive credentials that should no longer remain active. Use run history to distinguish an agent execution problem from a connector or external-account permission problem.

Organization Owners and Admins can open Settings, confirm the organization shown in the selector under Organization, and select Usage to review model spend, model usage over time, successful skill loads over time, per-member usage, per-agent usage, and activity. The charts share the selected date range. Spend totals, charts, activity amounts, and run details show the credits charged to the organization. Charges for choosing a message's level on Auto show as their own Auto routing line. They add spend but are not counted as runs, and they have no run trace. Image and video generation charges show under the image or video model that made them, not under the run's chat model; they add spend to that model but are not counted as its runs or tokens. Activity cost sorting and filters use that same amount; runs with no credit charge show zero. User stats shows member-attributed spend, tokens, and runs over time; use the member picker to filter both the chart and totals table. User avatars follow the member's current profile. Usage without member attribution remains included in Team totals and Activity but is excluded from User stats. User stats also shows your own activity insights and most-used skills; a member without access to these analytics sees their own above the restricted notice. On Team, the provider-reported token breakdown is under Advanced.

The model chart and Spend by model keep the five largest contributors visible and group the rest as Other. Hover, focus, or select Other to reveal up to five additional models in a compact panel. Selecting it keeps the panel open; select it again, click outside, or press Escape to dismiss it. Percentages in the panel are shares of Other, and a final row combines any remaining models. The chart breakdown follows its selected metric; the daily tooltip shows values for that day. Spend by model always shows credits charged. Large donut totals and chart axes use compact labels such as $100K; hover over the donut to see the exact amount. Model rows and the Other breakdown keep full amounts.

Agent stats shows only agent-attributed spend, tokens, and runs over time; use the agent picker to filter both the chart and totals table. Agent usage includes nested sub-agent runs and uses the agent's current name and avatar. Deleted agents remain as separate historical rows with a fallback identity. Ordinary chat, other non-agent work, and rows without agent attribution remain included in Team totals but are excluded from Agent stats. User stats and Agent stats are complementary attribution views: one run can be counted under the member who initiated it and the agent that executed it. Use an activity table column menu to sort the complete date-range result or search and filter values in that column. The Member column includes usage without member attribution when it exists.

In Activity, open a billed row to see its usage receipt. A run that generated an image or completed a video during that run lists its extra models beside the chat model. The receipt shows Cost by model. A background video has a separate charge under its video model. It adds spend without another run. The model filter finds the run by any of those models. When its source is still available and the row is a run, Inspect run opens the run trace. The run trace shows the outcome, charged usage per model call, and the run's recorded activity. Event payloads are collapsed until opened. Open conversation returns to the exact turn. You need access to the source conversation to open its trace. A restricted, deleted, or otherwise unavailable source shows no trace. The trace states when the exact model input was not captured; it does not reconstruct that input from later conversation state.

Workspace stats splits organization spend, tokens, runs, and agent runtime by the workspace recorded on each usage entry. Use the workspace picker to filter both the chart and totals table. Current workspaces show their current name and slug; entries without current metadata remain as separate historical rows with a generated fallback label. The table totals cover the complete selected date range, while charts are limited to the most recent 366 days and say when that limit applies.

The Usage summary also reports the charged total, purchased-credit balance, and current credit pace-window state. A run can be refused when the organization has no available balance, a pace window is exhausted, or spend has reached the organization limit, the workspace limit, or its initiating member's spend limit. The refusal message is the authoritative answer. Set organization and workspace limits in Settings → Billing → Spend limits. Organization Owners and Admins manage member spend limits through the organization member API; setting or clearing a limit is recorded in the audit log. Review those controls before enabling unattended work.

Select Billing in the same Organization group to manage what the organization pays for. It is an organization page rather than a workspace one, so it stays reachable for an administrator who cannot open any workspace, and an older workspace Billing link redirects to it. The Plan card names the current plan, its status, its seats and price, and when the period ends; Change plan opens a picker with a Personal and a Team side. Which plans it offers follows the organization's kind, and the plans an organization cannot buy are shown but not selectable. A personal organization selects Set up a team to create a separate team, choosing its region before naming it and reviewing its seats. If the team uses seats on joining, setup starts with 1 standard seat for You, team owner; review the displayed offer and renewal before Continue to payment. A remote choice continues at that region's d5s address. An existing team organization without a Team subscription selects Choose seats and start Team to check out that same organization, even when it has no workspace. An active Pro subscription upgrades to Max in place from that picker. Every other plan change is a card-only Stripe Checkout redirect, and every downgrade or cancellation is handled in the Stripe Billing Portal behind Manage in Stripe on the Payment & invoices card, which also serves card updates and invoice history.

A team organization's Plan card adds standard and premium seat steppers with Apply seat changes. The steppers respect committed capacity, including active members and pending invitations that need purchased seats, and they confirm before applying: an increase is invoiced immediately for the rest of the cycle, and a decrease is scheduled for the end of it with the seats usable until then. A scheduled decrease stays on the card with an Undo scheduled change control. The Usage credits card shows the purchased-credit balance and a Buy credits control that opens a top-up. On a Pro, Max, Team, Team+ or Enterprise plan, the top-up dialog also sets up auto top-up, which is off by default and charges the saved card when the balance falls below a threshold, or when a usage limit is full and purchased credits are below it; see Plans and credits. Top-ups are priced in US dollars for every organization; the card issuer converts. New Pro and Max subscriptions in euro show a fixed monthly price that includes applicable VAT. US-dollar subscriptions, Team seats, and top-ups show prices before VAT. Checkout shows tax and the total before payment. Existing subscription prices and discount terms stay the same; invoices show their applicable VAT. The plan and Team dialogs state that the subscription renews monthly until cancelled in Settings → Billing through Manage in Stripe and which terms the checkout checkbox accepts; the top-up dialog states that credits are delivered at once. An eligible consumer subscription shows Withdraw contract for 14 days. The separate confirmation records the statement before ending paid-plan access, processing any refund, and sending a downloadable acknowledgement by email. Emailing hello@d5s.tech remains available. See Plans and credits for the outcome. After paying, Stripe returns to this page and it confirms the plan or the credits once the payment has been processed.

Free organizations run the Light level only. Medium, High and hand-picked models are locked until the organization moves to a paid plan; a chat, agent or automation that stored another choice before a downgrade runs as Light. An organization Owner or Admin enables available models from Organization settings → Models, for every workspace in the organization. Model availability depends on the current plan and policy. If an expected model is unavailable, contact d5s before asking members to run the pilot.

New accounts need a paid plan; see Plans and credits. A Free organization starts with Light as its default. Paid organizations can use the levels and hand-picked models currently available to their account. Review Organization settings → Models for the current default and enabled choices. Downgrading to Free makes only Light available without deleting the saved paid-plan policy. After upgrading, saved paid-plan choices become available again when the account can still use them.

Models are set once for the organization and apply to every workspace in it. Open Settings from your profile menu, choose the organization in the selector under Organization, and select Models in that Organization group. On a narrow screen, use the Settings index. The page shows the level cards first. To pick models by hand, open Advanced at the bottom of the page and select Open catalog in the All models row; Models in the catalog's page title returns to the level cards. In the catalog, a list of model publishers, such as Anthropic or OpenAI, runs down the left side, and each publisher shows how many of its models are enabled. The most widely used publishers are listed first and the rest follow alphabetically. Select a publisher to list the current available model from each of its families beside it; on a narrow screen the publishers are a dropdown above the list. Each row is one line with the model name, an EU flag when the model runs in the EU, and a switch. Point to a row, or move focus to it, to see a short description of what the model is for and where the model runs for your organization: Amazon Bedrock or Azure OpenAI in the EU, Vercel AI Gateway, or No allowed route for a model that cannot be enabled. Select anywhere on a row to turn the model on or off. Models that the organization's current plan cannot use stay visible with disabled switches. The All / On / Off filter above the list carries the counts for the visible family list. Beside that filter, Search models matches model name, publisher, or catalog model identifier across every publisher. Every word you type must match, in any order. When the selected publisher has no match for a search or filter, the list moves to the first publisher that has one. The line under the page title reports how many models the search matched across the visible family list. The search and the filter apply together. A model you switch off while the On filter is selected keeps its row until you choose another publisher or filter, so the switch you just used does not disappear. A publisher's count and its bulk control always describe the whole publisher, not the filtered rows.

The Models page shows three level cards, Light, Medium and High. Each card names what the level is good for and shows relative speed and cost. d5s chooses the model for each level from the model options currently available to your account, and updates it when a better available model ships: every chat, agent, automation and dashboard on a level uses the new model from its next turn. If no model of a level can run with the providers your organization allows, work on that level uses another enabled model that can run, which can be from a different level. The model switches in the catalog control hand-picked models only; they do not change what a level runs. Select Default on one card to make it the default for new chats; switch Available off to hide a level from members (the default level and the last enabled level stay on). The catalog shows one current available model per family, with its version in the model name and a switch to enable it; the organization default select lists the three levels first. Older saved model choices now use the matching level. Chats that used a specific model move to its level the same way. A choice keeps its model when no level uses that model, or when the matching level is switched off. On Free, every saved choice moves to Light.

Where the model list is available, select a model family and reasoning effort in the model menu for your chat, agent, automation, or dashboard. The menu names the current available version. Your selection stays within that family through future level updates and uses its newest eligible version on the next turn. Existing saved catalog choices and organization defaults follow the same family rule. Enabling or disabling a family applies to its versions, so a new release of an enabled family does not need another switch. A saved level continues to follow d5s model updates, including when selected in an agent.

If a family's newest version is unavailable under the organization's access or settings, d5s uses an earlier available version in that family. If none is available, choose another enabled model or review the organization's settings. A model update does not replace the model in work already running or change historical model and usage records. Connected-subscription model choices keep their existing behavior.

Under Advanced on Organization settings → Models, turn on Fast to prefer the matching Fast variant across the organization. If that variant is unavailable under the current plan or policy, the regular model of the same version is used. This setting also applies when a level uses a catalog model. It does not change connected-subscription model access. Fast variants can use more credits, so review the displayed cost indication. The lightning icon beside chat model controls shows that Fast is enabled; its tooltip explains when the regular model is being used.

Newly cataloged models are labeled New for 30 days. Use the Models page to review availability. Each model row shows its publisher icon; its short description is in the row's tooltip. Choose reasoning effort in the chat or model menu; the Models page has no per-model reasoning control. A $$$ mark identifies the most expensive models; on Free, Pro, and Team plans the composer asks a member to confirm the first time they pick one. Provider and regional labels in the row's tooltip, including Amazon Bedrock and Azure OpenAI in the EU, show where each model runs. The available list depends on your organization's access and region. The Models page shows each available model once, and the default used for new work. Adding an available model does not change the organization default. Members use d5s credits. The organization's storage region does not by itself guarantee regional model inference; see Security and trust.

Use Turn all on or Turn all off above a publisher's list to turn that publisher's models on or off in one step; the control is omitted for a publisher with a single model. Set the organization default in the Organization default row at the top of the catalog, which lists only enabled models. The default model and the last remaining enabled model cannot be turned off, because either would leave the organization with no model to run. Turn all off always spares the organization default for the same reason, so a publisher holding the default keeps that one model enabled.

Under Advanced, Image model sets the model the agent's image generation tool uses for every agent across the organization's workspaces. The list is a short allow-list of image models, not the catalog above; each entry shows a rough cost per image, and the platform default is marked. A new organization starts on the platform default. The choice saves as soon as you pick it and applies to the next run. Members cannot change it, and an agent cannot choose a different image model for a single request.

If you see Video models under Advanced, it sets which video models an agent can propose, for every agent across the organization's workspaces. Open the list and select or clear a model. Models are grouped by tier, and each shows an estimated cost for an 8-second clip at its supported quality levels. All video models are allowed by default. At least one video model must stay allowed. Each change saves as soon as you make it and applies to the next video that an agent proposes. Members cannot change it. The control is not shown on the Free plan, because Free does not include video generation. The list also includes models for motion transfer and video editing. These use the same organization restrictions. Each video operation starts as a card that a person approves in the conversation. See Context and capabilities.

Under Advanced, the Providers row lists the providers that run the organization's models. Select Manage to open the Providers page; Models at the top of that page returns to the Models page.

When OpenAI Codex connection is available on the Models page, an organization Owner or Admin can connect one ChatGPT subscription through OpenAI's device login. Open the secure OpenAI page, enter the one-time code, and sign in with an account your organization authorizes for shared use across the organization's workspaces. d5s stores the resulting refreshable credential for the organization and never shows it to members. The organization's ChatGPT connection replaces any earlier workspace connection; an Owner or Admin reconnects once. Open the model count to enable verified Codex models, and select the shared runtime from the organization default control at the top of the Models page. Every member then inherits that connection and default for new work, while only organization Owners and Admins can reconnect, refresh, reconfigure, or disconnect it. Existing named agents that explicitly pin a catalog model keep that pin; choose Workspace default in the agent's Profile to restore inheritance.

Open the subscription row's three-dot menu for Reconnect or Disconnect. A connection needing attention shows Reconnect directly in its row. Disconnect always asks for confirmation. Reconnect when OpenAI revokes the login or the ChatGPT subscription changes. Disconnect when the organization should no longer use that subscription. The organization must allow connected subscriptions, and OpenAI usage remains attributed to the connected account and subject to that account's plan, limits, and terms. If the connection is disconnected, is no longer available to a workspace, or a personal or organization no-training setting applies, new work uses the organization's model settings instead. Work that already started may finish on the subscription. Availability shown on the page is authoritative.

When Grok or Claude subscription rows are available on the Models page, an organization Owner or Admin can connect an authorized Grok or Claude subscription for shared use across the organization's workspaces. Grok uses a one-time device code on xAI's sign-in page. Claude asks the administrator to run claude setup-token locally and paste the resulting setup token. d5s verifies and encrypts the credential, never redisplays it, and deletes it when an administrator disconnects. Every member and agent in the organization can use the active connection without seeing its credentials; only organization Owners and Admins can connect, reconnect, configure, or disconnect it. Every workspace in the organization shares the same connection; existing workspace connections were removed when this moved to the organization, so an Owner or Admin reconnects once.

A saved Light, Medium, or High choice, including the level chosen by Auto, applies to the organization's connected subscription when it offers a matching enabled model. The model shown for each level on the Models page reflects that choice. If no matching subscription model is available, the organization's catalog models apply.

Workspace default in an agent Profile shows its inherited configuration. A conversation using Auto can use a different model. Check the conversation's selected level and the matching model on the Models page. To use newly available Codex models, an organization Owner or Admin must refresh the connection's model list and enable the desired models. Refreshing the list keeps the existing enabled choices; it does not enable new models automatically.

An organization Owner or Admin can allow or block ChatGPT, Grok, and Claude subscription providers independently under the organization's provider policy. Use the organization default control at the top of the Models page to select one active subscription runtime across Codex, Grok, and Claude; enabling one disables the others so all members and agents resolve the same default. New work uses that runtime only while a workspace's plan or entitlement and the organization policy allow it. If no shared subscription runtime is active or available, new work uses the organization's catalog-model policy. Personal and organization privacy preferences continue to apply. Provider usage remains subject to the connected account's plan, limits, and terms.

Where the Project model control is available, a workspace Owner or Admin can open the model card beside the Project composer and select Workspace default, an enabled catalog model, or an enabled shared Codex model. The saved preference is shared: every member’s ordinary chats in that Project use the same route, and members who are not workspace administrators see the effective model without changing it. Named agents, automations, and dashboards retain their own model settings. Select Workspace default to remove the Project override.

Continue with Sharing and permissions, Connect and activate a connector, and Security and trust.

Check computer storage

If your workspace settings show Storage, open Settings → Workspaces → workspace name → Storage as a workspace owner or admin. Use Refresh to read disk usage. The read does not start or resize a computer. If it is stopped or unreachable, usage remains unavailable; saved files are retained.