Update 03-observability-sdk.mdx

docs/docs/observability/03-observability-sdk.mdx

@@ -176,11 +176,11 @@ def rag_workflow(query:str):
 
 ```
 
-## Excluding Inputs/Outputs Information from Capture
+## Redacting sensitive data: how to exclude data from capture
 
 In some cases, you may want to exclude parts of the inputs or outputs due to privacy concerns or because the data is too large to be stored in the span.
 
-You can achieve this by setting the `ignore_inputs` and/or `ignore_outputs` arguments to `True` in the instrument decorator.
+You can do this by setting the `ignore_inputs` and/or `ignore_outputs` arguments to `True` in the instrument decorator.
 
 ```python
 @ag.instrument(
@@ -192,7 +192,7 @@ def rag_workflow(query:str):
      ...
 ```
 
-If you need finer control, you can specify which parts of the inputs and outputs you want to exclude.
+If you want more control, you can specify which parts of the inputs and outputs to exclude:
 
 ```python
 @ag.instrument(
@@ -208,7 +208,7 @@ def rag_workflow(query:str, user_id:str):
      }
 ```
 
-If you need even finer control, you can alternatively specify a custom `redact()` callback, along with instructions in the case of errors.
+For even finer control, you can use a custom `redact()` callback, along with instructions in the case of errors.
 
 ```python
 def my_redact(name, field, data):
@@ -234,7 +234,7 @@ def rag_workflow(query:str, user_id:str):
      }
 ```
 
-Finally, if you want global guardrails, you can specify a global `redact()` callback that will be applied on top of everything else.
+Finally, if you want to set up global rules for redaction, you can provide a global `redact()` callback that applies everywhere.
 
 ```python
 def global_redact(
@@ -276,4 +276,4 @@ def rag_workflow(query:str, user_id:str):
           "result": ...,
           "pii": ...
      }
-```
+```