Merge branch 'main' into mason/vercel-marketplace-docs

masnwilliams · web-flow · commit 4fb634011866 · 2025-10-21T20:37:46.000-04:00
diff --git a/integrations/computer-use/anthropic.mdx b/integrations/computer-use/anthropic.mdx
@@ -4,12 +4,6 @@ title: "Anthropic"
 
 [Computer Use](https://docs.claude.com/en/docs/agents-and-tools/tool-use/computer-use-tool) is Anthropic's groundbreaking capability that enables Claude to interact with computers the way humans do—by looking at screens, moving cursors, clicking buttons, and typing text. This powerful feature allows AI agents to control web browsers, navigate interfaces, and perform complex tasks across applications.
 
-With Computer Use, Claude can:
-- **Navigate websites and applications** by interpreting visual interfaces
-- **Click buttons and fill forms** just like a human would
-- **Take screenshots** to understand and verify its actions
-- **Perform multi-step workflows** that span multiple applications or web pages
-
 By integrating Computer Use with Kernel, you can run these AI-powered browser automations on cloud-hosted infrastructure, eliminating the need for local browser management and enabling scalable, reliable AI agents.
 
 ## Quick setup with Computer Use
diff --git a/integrations/computer-use/gemini.mdx b/integrations/computer-use/gemini.mdx
@@ -2,30 +2,34 @@
 title: "Gemini"
 ---
 
-Google's [Gemini 2.5 Computer Use model](https://blog.google/technology/google-deepmind/gemini-computer-use-model/) is a specialized model built on Gemini 2.5 Pro's capabilities to power agents that can interact with user interfaces.
+[Gemini 2.5 Computer Use](https://blog.google/technology/google-deepmind/gemini-computer-use-model/) is Google's groundbreaking capability that enables AI models to interact with computers the way humans do—by looking at screens, moving cursors, clicking buttons, and typing text. This powerful feature allows AI agents to control web browsers, navigate interfaces, and perform complex tasks across applications.
 
 By integrating Gemini 2.5 Computer Use with Kernel, you can run these AI-powered browser automations on cloud-hosted infrastructure, eliminating the need for local browser management and enabling scalable, reliable AI agents.
 
-## Quick setup with our example template
+## Quick setup with Computer Use
 
-Get started quickly with our TypeScript template that demonstrates Gemini 2.5 Computer Use with Kernel.
+Get started with Gemini Computer Use and Kernel using our pre-configured app template:
 
-Check out the [Open-source Gemini Template](https://github.com/onkernel/ts-stagehand-google-cua-agent) repository for a complete working example that shows how to:
-- Set up Gemini 2.5 Computer Use with Kernel
-- Use Stagehand for browser automation
-- Run AI-powered web interactions on cloud infrastructure
+```bash
+npx @onkernel/create-kernel-app my-computer-use-app
+```
 
-## Benefits of using Kernel with Gemini Computer Use
+Choose `TypeScript` as the programming language and then select `gemini-cua` as the template.
+
+Then follow the [Quickstart guide](/quickstart/) to deploy and run your Computer Use automation on Kernel's infrastructure.
+
+## Benefits of using Kernel with Computer Use
 
 - **No local browser management**: Run Computer Use automations without installing or maintaining browsers locally
-- **Scalability**: Launch multiple browser sessions in parallel for concurrent automations
-- **Stealth mode**: Built-in anti-detection features for web interactions
+- **Scalability**: Launch multiple browser sessions in parallel for concurrent AI agents
+- **Stealth mode**: Built-in anti-detection features for reliable web interactions
 - **Session persistence**: Maintain browser state across automation runs
-- **Live view**: Debug your automations with real-time browser viewing
+- **Live view**: Debug your Computer Use agents with real-time browser viewing
+- **Cloud infrastructure**: Run computationally intensive AI agents without local resource constraints
 
 ## Next steps
 
-- Check out [live view](/browsers/live-view) for debugging your automations
+- Check out [live view](/browsers/live-view) for debugging your Computer Use automations
 - Learn about [stealth mode](/browsers/stealth) for avoiding detection
 - Learn how to properly [terminate browser sessions](/browsers/termination)
 - Learn how to [deploy](/apps/deploy) your Computer Use app to Kernel
diff --git a/integrations/computer-use/openai.mdx b/integrations/computer-use/openai.mdx
@@ -2,7 +2,9 @@
 title: "OpenAI"
 ---
 
-[Computer Use](https://openai.com/index/computer-using-agent/) is OpenAI's feature that enables AI models to interact with computers like humans do - through screen observation, cursor movement, and keyboard input. By integrating with Kernel, you can run Computer Use automations with cloud-hosted browsers, allowing your AI agents to navigate websites, fill forms, and interact with web applications autonomously.
+[Computer Use](https://openai.com/index/computer-using-agent/) is OpenAI's feature that enables AI models to interact with computers the way humans do—by looking at screens, moving cursors, clicking buttons, and typing text. This powerful feature allows AI agents to control web browsers, navigate interfaces, and perform complex tasks across applications.
+
+By integrating Computer Use with Kernel, you can run these AI-powered browser automations on cloud-hosted infrastructure, eliminating the need for local browser management and enabling scalable, reliable AI agents.
 
 ## Quick setup with our Computer Use example app
 
diff --git a/proxies/overview.mdx b/proxies/overview.mdx
@@ -84,7 +84,7 @@ When no longer needed, delete the proxy configuration:
 <DeleteProxySnippet />
 
 <Info>
-Deleting a proxy does not affect existing browser sessions that are currently using it. The configuration is only removed from your organization so it can't be used in future browser sessions.
+Deleting a proxy immediately reconfigures associated browsers to route directly to the internet.
 </Info>
 
 ## Limitations
diff --git a/proxies/residential.mdx b/proxies/residential.mdx
@@ -6,7 +6,7 @@ Residential proxies route traffic through real residential IP addresses. They su
 
 ## Configuration
 
-Residential proxies support multiple targeting parameters:
+Create a residential proxy with a target country:
 
 <CodeGroup>
 
@@ -16,10 +16,9 @@ const kernel = new Kernel();
 
 const proxy = await kernel.proxies.create({
   type: 'residential',
-  name: 'my-la-residential',
+  name: 'my-us-residential',
   config: {
-    country: 'US',
-    city: 'los_angeles'
+    country: 'US'
   }
 });
 
@@ -34,10 +33,9 @@ client = kernel.Kernel()
 
 proxy = client.proxies.create(
     type='residential',
-    name='my-la-residential',
+    name='my-us-residential',
     config={
-        'country': 'US',
-        'city': 'los_angeles'
+        'country': 'US'
     }
 )
 
@@ -54,4 +52,112 @@ browser = client.browsers.create(
 - **`state`** - Two-letter state code. Only supported for US.
 - **`city`** - City name (lowercase, no spaces, e.g., `sanfrancisco`, `newyork`).
 - **`zip`** - US ZIP code (5 digits). Conflicts with city and state.
-- **`asn`** - Autonomous System Number. Conflicts with city and state.
+- **`asn`** - Autonomous System Number. Conflicts with city and state.
+
+## Advanced Targeting Examples
+
+Kernel recommends using the least-specific targeting configuration that works for your use case. The more specific a configuration, the less available IPs there are, increasing the chance of a slow connection or no available connection (`no_peer` connection error).
+
+### Target by City
+
+Route traffic through a specific city:
+
+<CodeGroup>
+
+```typescript Typescript/Javascript
+const proxy = await kernel.proxies.create({
+  type: 'residential',
+  name: 'la-residential',
+  config: {
+    country: 'US',
+    state: 'CA',
+    city: 'los_angeles'
+  }
+});
+```
+
+```Python Python
+proxy = client.proxies.create(
+    type='residential',
+    name='la-residential',
+    config={
+        'country': 'US',
+        'state': 'CA',
+        'city': 'los_angeles'
+    }
+)
+```
+
+</CodeGroup>
+
+<Note>
+If the city name is not matched, the API will return the best 10 city names from the state to help you find the correct city identifier.
+</Note>
+
+### Target by State
+
+Route traffic through a specific state:
+
+<CodeGroup>
+
+```typescript Typescript/Javascript
+const proxy = await kernel.proxies.create({
+  type: 'residential',
+  name: 'ny-residential',
+  config: {
+    country: 'US',
+    state: 'NY'
+  }
+});
+```
+
+```Python Python
+proxy = client.proxies.create(
+    type='residential',
+    name='ny-residential',
+    config={
+        'country': 'US',
+        'state': 'NY'
+    }
+)
+```
+
+</CodeGroup>
+
+<Note>
+If the state name is not matched, the API will return the most-available 10 states.
+</Note>
+
+### Target by ASN
+
+Route traffic through a specific Autonomous System Number (ISP):
+
+<CodeGroup>
+
+```typescript Typescript/Javascript
+const proxy = await kernel.proxies.create({
+  type: 'residential',
+  name: 'comcast-residential',
+  config: {
+    country: 'US',
+    asn: 'AS7922'
+  }
+});
+```
+
+```Python Python
+proxy = client.proxies.create(
+    type='residential',
+    name='comcast-residential',
+    config={
+        'country': 'US',
+        'asn': 'AS7922'
+    }
+)
+```
+
+</CodeGroup>
+
+<Note>
+If the ASN is not matched, the API will return the most-available 10 examples.
+</Note>
