simplify privacy section

Author: obostjancic

docs/product/insights/agents/privacy.mdx

@@ -4,18 +4,22 @@ sidebar_order: 20
 description: "Learn how to control data collection and protect sensitive information in AI agent monitoring."
 ---
 
-By default, Sentry AI agent integrations respect your SDK's PII (Personally Identifiable Information) settings:
+## SDK PII Settings
 
-- **When Send Default PII is disabled** (default): Only metadata like model names, token counts, tool names, and execution times are collected
-- **When Send Default PII is enabled**: Full inputs, outputs, prompts, and responses from AI models and tools are captured
+By default, Sentry AI agent integrations respect your [SDK's PII settings](/platforms/javascript/guides/nextjs/data-management/data-collected/):
 
-## Data Scrubbing and Protection
+- `sendDefaultPii: false` - Only metadata like model names, token counts, tool names, and execution times are collected
+- `sendDefaultPii: true` - Full inputs, outputs, prompts, and responses from AI models and tools are captured.
+
+You can override this by configuring it on a function call level. For more details see [Configuration](/platforms/javascript/guides/nextjs/configuration/integrations/vercelai/#configuration).
+
+## Server side PII Scrubbing
 
 <Alert level="info">
 
 Sentry has built-in [Server-Side Data Scrubbing](/security-legal-pii/scrubbing/server-side-scrubbing/) that automatically detects and removes common sensitive data like credit card numbers, social security numbers, and passwords from most event data.
 
-However, Following AI agent span attributes may not be fully protected by these scrubbers.
+However, the following AI agent span attributes are not protected by default:
 
 - `gen_ai.prompt`
 - `gen_ai.request.messages`
@@ -26,22 +30,6 @@ However, Following AI agent span attributes may not be fully protected by these
 - `gen_ai.response.object`
 
 </Alert>
-If you wish to enable Data Scrubbing for any of these fields you can add them to **Additional Sensitive Fields** in **Security & Privacy** settings.
+If you wish to enable Data Scrubbing for any of these fields you can add them to **Global Sensitive Fields** in **Security & Privacy** [settings](https://sentry.io/orgredirect/organizations/:orgslug/settings/organization/security-and-privacy) or to **Additional Sensitive Fields** in Project settings under **Security & Privacy**.
 
 ![Additional Sensitive Fields](./img/data-scrubbing.png)
-
-## Overriding Collection Settings
-
-Using Vercel AI SDK you can override the global PII settings for specific AI operations by setting `recordInputs` and `recordOutputs` to `true`:
-
-```javascript
-const result = await generateText({
-  model: openai("gpt-4o"),
-  prompt: userQuery,
-  experimental_telemetry: {
-    isEnabled: true,
-    recordInputs: true,
-    recordOutputs: true,
-  },
-});
-```