Merge pull request #596 from AssemblyAI/devin/1770133164-prompt-engineering-edits

Update prompt engineering page examples

Author: ryanseams

fern/pages/02-speech-to-text/pre-recorded-audio/prompt-engineering.mdx

@@ -44,7 +44,7 @@ For consistent proper-noun accuracy or domain vocabulary, you'll usually need **
 **Sample prompt 1: Simple, readable transcription**
 
 ```text
-Transcribe verbatim
+Transcribe this audio
 ```
 
 Characteristics of prompt output:
@@ -259,8 +259,7 @@ in the language they are spoken.
 ```
 
 ```text
-Preserve natural code-switching between English and Spanish. Retain spoken
-language as-is (correct "I was hablando con mi manager").
+Preserve natural code-switching between English and Spanish. Retain spoken language as-is with mixed language words.
 ```
 
 **Note:** Requires `language_detection: true` on your request. If a single language code is specified, the model will try to transcribe only that language.
@@ -284,7 +283,7 @@ Use digits for numbers, percentages, and measurements.
 ```
 
 ```text
-Format financial figures with standard notation (Q3 revenue over third quarter revenue).
+Format financial figures with standard notation and format numbers for maximum readability.
 ```
 
 ---