Give the browser a clear job.

Describe a task, set the authorized target and credentials, and let Molar carry out the browser steps. Use the result in a script, dashboard, or agent workflow.

Browser taskIllustrative workflow
billing.acme.test
Browser taskFind August invoice

Aug 2026 Paid

Documentinvoice_august_2026.pdf


Downloaded

Task to result

Start with a goal such as finding an invoice or completing an approved form.

Browser aware

Work through the interface and state your users see.

Built for handoff

Return structured status and artifact references to the next tool.

Useful jobs

Run a bounded task against an authorized app: download a report, update a project field, or verify a page state.

  • Forms
  • File downloads
  • Page checks
Go to documentation
Browser taskIllustrative workflow
billing.acme.test
Browser taskFind August invoice

Aug 2026 Paid

Documentinvoice_august_2026.pdf


Downloaded

Keep automation accountable

Define target, scope, credentials, and expected result before execution. Completed, failed, and blocked outcomes stay distinct.

  • CLI and MCP
  • Scoped access
  • Inspectable evidence
Talk through your use case
Checkout journeyIllustrative workflow
checkout.acme.test
PaymentAcme Pro plan4242 4242 4242 424208 / 28 · Test card
Signed callbackPayment webhookPOST /webhooks/payment signature verified
Order #1042ConfirmedReceipt → test inbox

A few things
you might be wondering.

Have a specific workflow in mind?
Let’s talk it through

Is this only for testing?

No. Molar supports authorized browser tasks as well as QA journeys.

Can an agent start a task?

The CLI and MCP provide agent accessible entry points with structured results.

Can automation make irreversible changes?

Sensitive actions depend on configured workflow and authorization controls.

Automate a browser task.

Choose a concrete workflow. We’ll help you get the right setup for your application.