# Browser surface Source: https://docs.ideharmony.com/desktop/browser The browser surface puts a real Chromium pane inside the workspace, with an element inspector aimed at agents rather than at you. It exists so an agent can see a running application instead of reasoning about it from source. > [!SECURITY] > Every page a browser surface loads is untrusted input. A web page can contain > text written specifically to steer an agent that reads it. Treat browser > content exactly as you would treat a repository written by a stranger — see > [security overview](/docs/security). ## Two different things | Thing | What it is | |---|---| | **Browser pane** | An embedded Chromium surface with a toolbar, shown in your workspace | | **Driven session** | A separately-controlled browser session used for automation | They are not the same surface, and a driven session is not necessarily what you are looking at. ## Profile partitioning Browser surfaces use partitioned profiles rather than one shared browsing context. A surface's cookies and storage are its own. > [!IMPORTANT] > Partitioning is about isolation between surfaces, not about anonymity. If you > sign in to something in a browser surface, that session persists in that > partition. ## The element inspector An overlay that exposes page structure in a form an agent can act on. This is distinct from Inspect mode, which inspects Harmony's own interface. Two inspectors, two targets: | Inspector | Inspects | |---|---| | Browser element inspector | The page loaded in a browser surface | | Inspect mode | Harmony's own UI | ## Agent access Browser automation is exposed to agents through MCP tools — navigation, interaction, extraction, and screenshots. > [!WARNING] > An agent driving a browser can reach anything that browser can reach, > including sites you are signed in to within that partition. This is a real > capability, not a sandbox. Decide deliberately before pointing an agent at a > browser surface with authenticated sessions in it. ## Checking what it built > [!NOTE] > `browser_check` and its baselines are **not in 3.25.8**, the current > release. They arrive with the next release. `browser_check` is one tool call that loads a URL (or uses the page already open), waits for it to settle, and returns a screenshot, the URL it ended on, and the console errors and warnings from that load only. Agents use it after a UI change, including against their own workspace's local dev server. It can also tell an agent what changed visually. `saveBaseline: "home"` stores the capture as a named baseline for the project, and a later call with `baseline: "home"` compares against it. It returns the number and share of pixels that changed, the box around the change, and a diff image with changes in red. `tolerance` sets how much per-pixel difference counts as render noise (default 24 of 255). A page that changed size says so instead of being compared. ## Practical guidance - **Use a clean partition for agent work.** Do not hand an agent a browser carrying your own authenticated sessions unless that is specifically the task. - **Read what came back.** Content extracted from a page is input to the model; it is not a fact. - **Prefer navigating to a specific URL** over asking an agent to search and choose. Fewer opportunities for the page to influence the plan. ## Troubleshooting | Symptom | Where to look | |---|---| | Page loads but the agent cannot interact | Confirm the surface is the one being driven | | Session lost between runs | Check which partition the surface uses | | Renders but appears blank in screenshots | GPU/rendering; see [performance](/docs/troubleshooting/performance) | ```powershell harmony doctor ``` ## Related - [Security overview](/docs/security) - [MCP](/docs/customization/mcp) - [Harmony Desktop](/docs/desktop)