diff --git a/fern/pages/02-speech-to-text/pre-recorded-audio/prompt-engineering.mdx b/fern/pages/02-speech-to-text/pre-recorded-audio/prompt-engineering.mdx
index 00c149dd..d7ab54e6 100644
--- a/fern/pages/02-speech-to-text/pre-recorded-audio/prompt-engineering.mdx
+++ b/fern/pages/02-speech-to-text/pre-recorded-audio/prompt-engineering.mdx
@@ -372,22 +372,17 @@ amicus curiae).
 
 ### Medical transcription
 
-Best for: Clinical consultations, medical dictation, patient encounters
+Best for: Clinical documentation, medical dictation, patient-provider conversations
 
 ```text
-Mandatory: Preserve all clinical terminology exactly as spoken including drug
-names, dosages, and diagnostic terms.
+Mandatory: Preserve all clinical terminology exactly as spoken including drug names, dosages, and diagnostic terms.
 
-Required: Capture every hesitation, false start, and filler word (um, uh, ah)
-as spoken.
-
-Non-negotiable: Pharmaceutical accuracy (omeprazole over omeprizole,
-metformin over metforman, hypertension over high blood pressure).
+Required: Capture every hesitation, false start, and filler word (um, uh, ah) as spoken.
 
 Label physician and patient speech clearly when identifiable.
 ```
 
-**Why it works:** Prioritizes medical accuracy with explicit drug name examples showing error patterns, while preserving verbatim speech for documentation compliance.
+**Why it works:** Combines authoritative language (Mandatory, Required) with explicit disfluency examples, while ensuring clinical terminology accuracy and clear speaker attribution for medical documentation.
 
 ---