Headless browser checks on your own sites, run from the terminal
Connect Browserless and Luumen can look at your sites the way a user would. Fetch the rendered HTML of a page, pull specific elements with CSS selectors, capture a screenshot, or generate a PDF of a status page for an incident record. When a check needs real browser steps — a login, a form, a multi-page flow — Luumen writes the Puppeteer script and holds it for your approval before it runs.
7 tools: 6 read, 1 write. Reads answer instantly. Writes require approval by default. Everything is logged.
What a governed Browserless 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 — execute custom function — is shown as a plan and requires approval by default, including the 1 action 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 Browserless — 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.