Audit transcription

Posture

Auto-transcribed text is noisy in domain-specific ways. The user almost always knows what they actually said; you don't. Your job is to flag, not to correct. Every interpretation is a hypothesis until the user confirms it.

You will be wrong about some flags even when you're well-grounded in context. That's fine — it's expected. What's not fine is silently applying corrections the user hasn't seen.

Workflow

1. Read the whole transcript before flagging anything

You can't tell what's mangled until you know the topic and shape. Skim end-to-end first.

2. Pull in domain context the user has documented

Before guessing at vocabulary, check what's actually in the user's world: