BrowserAct
for LuumenAI

Check BrowserAct runs, then start or resume a workflow as an approved step

Connect BrowserAct with an API key and Luumen can read your workspace directly: which workflows exist, what inputs they expect, which tasks are running, paused, or failed, and what each run produced. When a run needs to be started, resumed, or canceled, that step is previewed and approved first, then recorded.

The BrowserAct toolbox

11 tools: 7 read, 4 write. Reads answer instantly. Writes require approval by default. Everything is logged.

  • ReadGet TaskReturn either a task's current status or its full progress, outputs, files, live-view details, and failure information.
  • ReadGet WorkflowReturn a custom workflow's metadata and expected input parameter definitions before a run.
  • ReadGet Workflow TemplateReturn an official template's metadata and expected input parameter definitions before a run.
  • ReadList Proxy RegionsReturn the supported proxy region names and codes for official template runs.
  • ReadList TasksReturn one cursor-controlled page of workflow tasks, optionally filtered by status, workflow, name, or creation time.
  • ReadList WorkflowsReturn one cursor-controlled page of custom workflows in the connected workspace.
  • ReadList Workflow TemplatesSearch official BrowserAct workflow templates and return one cursor-controlled page of summaries.
  • WriteCancel TaskImmediately and permanently cancel a running BrowserAct task. Approval by default
  • WriteResume TaskResume a paused task from its current state. Approval by default
  • WriteRun WorkflowStart a custom BrowserAct workflow. Approval by default
  • WriteRun Workflow TemplateStart an official BrowserAct workflow template. Approval by default

One prompt, start to finish

What a governed BrowserAct run looks like inside Luumen.

Questions

How does LuumenAI connect to BrowserAct?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

Can LuumenAI change things in BrowserAct on its own?

Read actions answer immediately. Anything that writes — cancel task, resume task, run workflow, run workflow template — 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.

Who gets access to the integration?

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.

Is there an audit trail?

Every call to BrowserAct — 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.

Put BrowserAct to work with Luumen

Connect in minutes. Every action scoped, approved, and audited from day one.