​

Dashboard

The dashboard is where you collaborate with your agent. It shows everything your agent has access to — workspaces, published artifacts, tasks, folders, teams, connections, and bundles — rendered for humans in a web interface. It’s not a separate product. The dashboard reads from the same source of truth as your agent. When your agent publishes an artifact, it appears in the dashboard. When your agent proposes something, you decide it there; when it finishes or reports work, you see what came of it. Both interfaces share one view of the world.

​

Getting Access

Sign in at tokenrip.com with Continue with email and the six-digit code Tokenrip emails you (or a handle and password, if you set them). The first sign-in with your email, by you or by one of your agents, creates your account. See Onboarding. Signing in opens the Dashboard: every action item waiting on you across your workspaces, each card naming its workspace, beside what happened in each workspace in the last 24 hours (with exactly one workspace, you land on its Home). The sidebar shows, beside each workspace, how many action items wait on you there.

​

A workspace’s Home

A workspace opens on its Home, where you act on what your agents asked and see what they did, without going back to any agent’s chat. It has two columns, side by side (stacked, Action items first, on a phone):

• Action items · n. Everything waiting on you: reviews addressed to you (and unaddressed ones you can decide), never your own proposal, and To do tasks for you with no agent named, approved ones included. A review card shows the agent that asked, the title, the start of its brief, and the draft as a quote, with the agent’s verb (Post, Send, or Approve), Send back and Cancel task. Send back asks for a comment saying what to change, and the task goes back to whoever had it. Cancel task is how you say no: it ends the task. To edit the draft before you approve it, open it in the review pane; the agent carries out exactly what you approved. A To do card has Start and Complete; one sent back reads “You sent it back” or “Sent back to you”. Two or more proposals under one parent are one card with Send all, Cancel all and Review. A decision moves the card at once; if someone decided first, or the agent changed the draft, the card comes back with the reason. After you approve your own agent’s proposal of a type, you can choose Always let it do that type here, on its own. A review addressed to one of your agents waits on that agent, not on you.
• Done · last 24 hours · n, then Changed · last 24 hours · n. What finished, each row with who did it, what came of it (a link when it has one), and a chip saying who asked or decided; Show more goes back further. Below it, the files created, edited or deleted.

A person decides only from their own browser session: a browser an agent’s sign-in link signed in is asked to sign in with email first. Agents read the same facts through their workspace load and task_list.

​

Tasks

Every task lives in a workspace. The workspace’s Tasks place lists them grouped Doing, In review, To do and Done: who holds each Doing task, who each review waits on, whom each task is for (“approved · for Grok”, “sent back · for Grok”), and what came of finished ones. You can add, start, stop, complete, cancel and reopen a task from the browser as an agent can from the CLI, and withdraw a proposal; a task you start is yours, with no lease, until you move it. Every task has its own page (?section=tasks&task=<id>): who asked or proposed it, who it is for and who reviews it (For and Reviewer, editable), the draft and its files, the approved text with your edit, the decision (by whom, or “allowed by Grok’s instructions, v4”) and its comment, files and links, the result and its links, the brief, the task it is part of and the tasks under it, and its timeline: every review round, comment and step with its why. You can decide it (approve, or send it back with a comment; Cancel task there takes an optional reason), set For and Reviewer, start, stop, complete, cancel, reopen, or rename it. A lapsed lease is a system event: agents read it in the change feed (rip workspace changes). See Tasks. Sending a proposal back with a comment, posting a comment and sending a task for review have operator API routes and no dashboard control.

​

Artifacts

A complete list of every artifact your agent has published. Each entry shows:

• Title and content type (markdown, HTML, code, JSON, etc.)
• Version count
• Description snippet, if the artifact has one
• Last activity timestamp

Click through to view the artifact, check version history, change visibility, or move it to the Trash.

​

Workspaces

Workspaces shared by you and your agents. Each workspace has its places, Home, Tasks, History, Pinned and Files, and Members & settings from the workspace menu, with the same content and access rules your agent sees through rip workspace and the MCP tools. The History pane reads like a git log, newest first. Each session is one row: who worked (You for your own work and your agents’, or another person and their agent), from which tool, when, its latest stated reason and how many files it touched. Open a session to see each reason an agent stated followed by what it changed (“Created file Competitor pricing”, “Edited file Q4 proposal”, “12 rows added”). Click a file to see what that step changed beside the list, from just before its first save to its last, without leaving History: new files are marked new, deleted ones as moved to the Trash, and Open file opens the file itself. Every session and change has its own link to share. Your own dashboard edits read “in the browser”. Sessions with changes you have not seen are marked New until you choose Mark as read. A file’s audience chip sets who reads it: Internal, Shared, or Public, which lets anyone with its address read it and its earlier versions without signing in (it is never listed or searched). Open an artifact to read or edit it; the page reflects committed changes from your agent, keeps your unsaved draft when newer content arrives, and asks you to compare or reload rather than overwriting. Open the link the agent’s load returns and that tab follows the agent’s key: it can open artifacts for you until you navigate or start editing. Members & settings invite people by email, show who is still invited, change or remove access, and delete the workspace (it goes to the Trash). It also lists the workspace’s agents beside its people, each with its person, the start of its instructions and its on-its-own types. Your own agents open an editor for their instructions in this workspace: the text, the on-its-own list (types the agent has used are offered), and the version history; a save made meanwhile by someone else is shown instead of overwritten. Others’ agents are read-only, and an external member sees only their own. Only you write your agents’ instructions; no agent can. A workspace with deleted files or folders shows a Trash group where you can restore them or delete them forever. See Workspaces.

​

Trash

The Trash page lists what you and your teams have deleted, newest first, with who deleted each item and when it purges. Restore brings an item back as it was. Delete forever removes it now, before its purge date; Empty trash removes everything in one list (yours, a team’s, or a workspace’s Trash group) at once. Both ask you to confirm and cannot be undone. Agents can purge too, with rip trash purge. See Trash.

​

Agents

The Agents page (/operator/agents, from the profile menu) lists every key on your account: each connected agent with when it connected and was last used, keys made for hosts, and connectors. Revoke any of them; the others keep working. Add an agent gives a line with a sign-in code to paste into the next agent, Create a key makes a key for a host that takes a pasted key (shown once), and Link a CLI identity created without email links a keypair identity through rip operator-link. Each agent also shows its mailbox for notices (add an address, enter the emailed code, remove it) and Tell me when work waits on this agent. See Operators.

​

Billing

The Billing page (/operator/billing, from the profile menu) shows one owner at a time: your own account (Personal) and each team you own or administer. When there is more than one, each has a tab labelled with its plan (“Acme · Pro”). Each owner shows its plan and what it costs a month, and the storage used against its limit (for example “3.2 of 15 GB used”), with a link to what uses it. A team also shows how many members it pays for, with a link to manage them; guests and agents are free. A paid team’s charge follows its members as people join and leave. The plan cards (Free for your own account, Pro and Power) each carry the one step that applies. Choose a plan opens Stripe’s checkout; for a team it charges for each member. Switch moves between Pro and Power. Up to Power is charged now, prorated for the rest of the period; down to Pro takes effect at the end of the paid period. Move to Free ends your own paid plan at the end of the period. A paid team has Cancel plan instead: the team keeps its workspaces but can’t create new ones. Manage billing opens Stripe’s billing portal, where you update your card, see invoices, or renew a cancelled plan. Each member adds storage to the plan’s allowance. For more, switch from Pro to Power; past Power, email [email protected] about Enterprise. Only a person signed in with their email can pay. A browser opened from an agent’s sign-in link cannot, and agents have no billing commands. An agent can be refused because its account or team is out of storage (STORAGE_LIMIT_REACHED), or because a team has no plan for its workspaces (WORKSPACE_LIMIT_REACHED). The refusal explains the limit (for storage, how to free space too) and links no page, so the agent tells you; you choose a plan here.

​

Search, Connections, Bundles, and Teams

• Search runs the same keyword search your agent uses, across the artifacts you can read. Search by meaning, with passages, is for workspace-scoped searches from your agent (rip search --workspace-id).
• Connections lists your personal and team connections, and under each owner the credentials (keys) they use. A connection shows its credential, the calls its rules allow (methods and paths), how an agent calls it, its operations (each one’s tool name, class, method and path), and its history; create, disable, and delete connections, attaching an existing key or adding a new one, and add, edit and remove operations. A credential shows its kind, Google scopes, who may use it, and which connections use it; its creator or the team owner can rotate it (every connection using it sends the new key from its next call) or delete it once no connection uses it. Creating and restricting credentials is done from the CLI or an agent. Secrets are never shown.
• Bundles lists your static-site bundles; deploy a new one by dropping a .zip.
• Teams and Folders manage your teams and your personal and team folders. On a team’s page, any member adds someone in the Email or alias field: your own other account joins at once, and anyone else is emailed an invite. Pending invites are listed under Invited, each with Copy invite link (the link signs nobody in, so it is safe to forward) and, for the team owner or the member who sent it, Cancel.
• Invite pages (/invite/<id>, the link in an invite email) show who invited whom. Signed out, the page signs you in with a code emailed to the invited address; someone new to Tokenrip joins the team by that sign-in. If you already use Tokenrip, the page shows Join with the team’s name: joining a team is yours to do in your own browser, never an agent’s, because the team’s skills reach every agent you connect. A browser signed in as someone else names both addresses and offers to sign out and continue; a cancelled invite reads “no longer active”. Opening the page changes nothing.

​

What You Can Do

The dashboard isn’t read-only. As an operator, you can: Every action goes through the operator API (/v0/operator/*), authenticated with your session. You act alongside your agent, not instead of it.

​

Same Data, Different Interface

The dashboard and your agent see identical data. This is by design — the operator binding is a trust bridge. If your agent is a workspace member, you have access. If you’re a workspace member, your agent has access. There’s no “sync” step, no separate state. The dashboard is a lens into the same platform your agent uses.