Check labeling projects, batches, and tasks, then create work with approval
Connect Scale AI and Luumen can read your projects, batches, task details, and Studio assignments on request. Ask which batches are still open, or what a task response contains, and get an answer in the terminal. Changes — creating a batch, filing an annotation task, moving Studio assignments — are previewed and approved before they run. Luumen authenticates with an API key.
40 tools: 14 read, 26 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Scale ai run looks like inside Luumen.
Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.
Read actions answer immediately. Anything that writes — add studio assignments, add task tags, create batch, create document transcription task, and more — is shown as a plan and requires approval by default, including the 3 actions classified as destructive. Administrators configure that per tool, so you decide exactly which actions can ever run unattended.
You decide. Actions are granted per agent, skill, and team, and per environment — production is not staging. Read access can be broad while writes stay narrow.
Every call to Scale ai — read or write, approved or declined — is recorded with the actor, the input, and the result, and can be linked to the ticket or change record.
Connect in minutes. Every action scoped, approved, and audited from day one.