Browser Agent
Browser Agent lets a PENTER agent operate the scoped application while the operator can reason about browser state, network behavior and the action timeline alongside the rest of the engagement.
Use Browser Agent for stateful application work
Web testing often depends on navigation order, authentication state, form state and application-side behavior. Browser Agent keeps those interactions inside the same engagement rather than forcing the agent to reason from disconnected screenshots or raw HTTP alone.
Rendered state
Interaction
Correlated context
Supported agent browser actions
| Action | Purpose | Typical inputs |
|---|---|---|
| navigate | Open a URL in the scoped browser. | url |
| snapshot | Capture current browser/application state for the agent. | none |
| elements | Inspect actionable/visible elements before interacting. | none / current page |
| click | Activate a selected page element. | selector |
| type | Enter text into an input/control. | selector, text |
| press | Send a key such as Enter, Escape or navigation keys. | key |
| scroll | Move the page viewport. | direction, amount |
| reload | Reload the current page. | none |
Packaged Desktop downloads Browser Agent Chromium on first use
Playwright Chromium is intentionally not embedded in the Windows installer. The packaged Browser Agent uses a dedicated headless Chromium download stored under PENTER user data.
- The first Browser Agent start shows the download size and waits for operator confirmation.
- The browser zip is downloaded from the Playwright CDN into the PENTER user-data browser directory.
- PENTER verifies the downloaded artifact against a pinned SHA-256 before using it.
- Later launches reuse the installed browser instead of downloading it again.
- Development builds use the Playwright browser installation from the local development environment.
Browser state belongs to the engagement
Authentication cookies, navigation position and selected application state can materially change what the agent can see. Keep browser sessions aligned with the same workspace/authorization boundary.
- Do not reuse an authenticated browser session across unrelated customer workspaces.
- Confirm the visible host belongs to the current authorized engagement before active interaction.
- Use snapshots/elements to ground the model in current state after major navigation changes.
- For API-only verification, prefer a direct HTTP tool when a full browser is unnecessary.
Network, console and element-selection context
The Desktop Browser Agent view maintains dedicated network and console logs beside the rendered browser frame. The operator can open the inspector, switch between those views, and use Select element mode to turn a point in the rendered page into structured DOM context.
- Select element resolves the DOM node at the clicked page coordinate and derives a CSS selector.
- Selected context includes bounded element text/HTML and useful attributes such as id, name, type and href.
- The selected element can be pinned into the wider PENTER browser/engagement context for later agent work.
- Browser observations include new console messages and new network requests so UI actions can be correlated with application behavior.
- The Browser Agent action loop has a bounded action limit rather than running without a ceiling.
Recommended Browser Agent workflow
| Step | Action | Reason |
|---|---|---|
| 1 | Navigate to the authorized target. | Establish browser context. |
| 2 | Snapshot / inspect elements. | Ground the agent in current UI state. |
| 3 | Perform one bounded interaction. | Keep causality clear. |
| 4 | Inspect resulting state/network/console. | Determine what actually changed. |
| 5 | Repeat or switch to HTTP/tool verification. | Use the cheapest reliable surface for evidence. |
| 6 | Attach relevant evidence to the candidate finding. | Preserve reproduction context. |
Browser Agent troubleshooting
Ready to get started?
Follow the setup guide, install the current approved Desktop release, and connect your account.