Update simulator-interaction-data.md

Author: ShawnJackson

articles/ai-foundry/how-to/develop/simulator-interaction-data.md

@@ -71,7 +71,7 @@ Prepare the text for generating the input to the simulator:
 - **Page retrieval**: Fetches the Wikipedia page for the identified title.
 - **Text extraction**: Extracts the first 5,000 characters of the page summary to use as input for the simulator.
 
-### Specify application Prompty
+### Specify the application Prompty file
 
 The following `application.prompty` file specifies how a chat application behaves:
 
@@ -111,7 +111,7 @@ given the conversation history:
 {{ conversation_history }}
 ```
 
-### Specify target callback that you want to simulate against
+### Specify the target callback to simulate against
 
 You can bring any application endpoint to simulate against by specifying a target callback function. The following example shows an application that's an LLM with a Prompty file (`application.prompty`):
 
@@ -147,17 +147,17 @@ async def callback(
     }
 ```
 
-The callback function above processes each message generated by the simulator.
+The preceding callback function processes each message that the simulator generates.
 
 ### Functionality
 
-- Retrieves the latest user message.
-- Loads a prompt flow from `application.prompty`.
-- Generates a response by using the prompt flow.
-- Formats the response to adhere to the OpenAI chat protocol.
-- Appends the assistant's response to the messages list.
+- Retrieves the latest user message
+- Loads a prompt flow from `application.prompty`
+- Generates a response by using the prompt flow
+- Formats the response to adhere to the OpenAI chat protocol
+- Appends the assistant's response to the messages list
 
-With the simulator initialized, you can now run it to generate synthetic conversations based on the provided text.
+With the simulator initialized, you can now run it to generate synthetic conversations based on the provided text:
 
 ```python
     model_config = {
@@ -322,7 +322,7 @@ azure_ai_project = {
 > [!NOTE]
 > Adversarial simulation uses the Azure AI safety evaluation service and is currently available only in the following regions: East US 2, France Central, UK South, Sweden Central.
 
-### Specify target callback to simulate against for adversarial simulator
+### Specify the target callback to simulate against for the adversarial simulator
 
 You can bring any application endpoint to the adversarial simulator. The `AdversarialSimulator` class supports sending service-hosted queries and receiving responses with a callback function, as defined in the following code block. The `AdversarialSimulator` class adheres to the [OpenAI messages protocol](https://platform.openai.com/docs/api-reference/messages/object#messages/object-content).
 
@@ -335,7 +335,7 @@ async def callback(
     query = messages["messages"][0]["content"]
     context = None
 
-    # Add file contents for summarization or re-write.
+    # Add file contents for summarization or rewrite.
     if 'file_content' in messages["template_parameters"]:
         query += messages["template_parameters"]['file_content']
 
@@ -431,7 +431,7 @@ The outputs consist of two lists:
 
 Run two evaluation runs with `ContentSafetyEvaluator` and measure the differences between the two datasets' defect rates.
 
-*Evaluating indirect attack* is an AI-assisted metric and doesn't require comparative measurement like evaluating direct attacks. You can generate an indirect attack jailbreak-injected dataset with the following, and then evaluate with `IndirectAttackEvaluator`.
+*Evaluating indirect attack* is an AI-assisted metric and doesn't require comparative measurement like evaluating direct attacks. You can generate an indirect attack jailbreak-injected dataset with the following code, and then evaluate with `IndirectAttackEvaluator`.
 
 ```python
 indirect_attack_simulator=IndirectAttackSimulator(azure_ai_project=azure_ai_project, credential=credential)
@@ -548,7 +548,7 @@ outputs = await simulator(
 
 To convert your messages format to JSON Lines (JSONL) format, use the helper function `to_json_lines()` on your output.
 
-#### Convert to question answer pairs
+#### Convert to question/answer pairs
 
 To convert a single turn chat format to `Question and Answering` pair format, use the helper function `to_eval_qr_json_lines()` on your output.