Run Browse.ai robots, check task history, and set up change monitors
Browse.ai turns websites into structured data through recorded robots. Connect it with an API key and Luumen can list your robots, read task history, check the Browse.ai task queue, and see which webhooks are wired up. When something needs to change — a re-run, a new monitor, a webhook — Luumen shows the plan first and waits for your approval.
11 tools: 5 read, 6 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Browseai 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 — bulk run tasks, create monitor, create webhook, delete a specific monitor, and more — is shown as a plan and requires approval by default, including the 2 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 Browseai — 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.