You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: docs/basics/agent.mdx
+2-2Lines changed: 2 additions & 2 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -117,7 +117,7 @@ MCP integrations enable agents to be more powerful by combining browser automati
117
117
</Tip>
118
118
119
119
<Warning>
120
-
Stagehand uses a 1024x768 viewport by default (the optimal size for Computer Use Agents). Other viewport sizes may reduce performance. If you need to modify the viewport, you can edit in the [Browser Configuration](/configuration/browser).
120
+
Stagehand uses a 1288x711 viewport by default (the optimal size for Computer Use Agents). Other viewport sizes may reduce performance. If you need to modify the viewport, you can edit in the [Browser Configuration](/configuration/browser).
121
121
</Warning>
122
122
123
123
@@ -291,7 +291,7 @@ if (firstResult.success === true) {
291
291
**Problem**: Agent clicks on wrong elements or fails to interact with the correct UI components
292
292
293
293
**Solutions**:
294
-
- Ensure proper viewport size: Stagehand uses `1024x768` by default (optimal for Computer Use models)
294
+
- Ensure proper viewport size: Stagehand uses `1288x711` by default (optimal for Computer Use models)
295
295
- Avoid changing viewport dimensions as other sizes may reduce performance
You might've heard of [Claude Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use) or [OpenAI's Computer Using Agent](https://openai.com/index/computer-using-agent/).
17
+
You might've heard of [Gemini Computer Use](https://blog.google/technology/google-deepmind/gemini-computer-use-model/), [Claude Computer Use](https://www.anthropic.com/news/3-5-models-and-computer-use), or [OpenAI's Computer Using Agent](https://openai.com/index/computer-using-agent/).
18
18
19
19
These are powerful tools that can convert natural language into actions on the computer. However, you'd otherwise need to write your own code to convert these actions into Playwright commands.
20
20
21
-
Stagehand not only handles the execution of Computer Use outputs, but also lets you hot-swap between OpenAI and Anthropic models with one line of code.
21
+
Stagehand not only handles the execution of Computer Use outputs, but also lets you hot-swap between Google, OpenAI, and Anthropic models with one line of code. You can find more information on the performance of different computer use models by visiting our [evals page](https://www.stagehand.dev/agent-evals).
22
22
23
23
## How to use a Computer Use Agent in Stagehand
24
24
@@ -29,7 +29,7 @@ Stagehand lets you use Computer Use Agents with one line of code:
29
29
30
30
Computer Use Agents will often return XY-coordinates to click on the screen, so you'll need to configure your browser dimensions.
31
31
32
-
If not specified, the default browser dimensions are 1024x768. You can also configure the browser dimensions in the `browserbaseSessionCreateParams` or `localBrowserLaunchOptions` options.
32
+
If not specified, the default browser dimensions are 1288 x 711. You can also configure the browser dimensions in the `browserbaseSessionCreateParams` or `localBrowserLaunchOptions` options.
33
33
</Note>
34
34
35
35
@@ -53,8 +53,8 @@ const stagehand = new Stagehand({
0 commit comments