UX Writing Audit

Copy debt is invisible until it isn't: users stall on a button they don't trust, support tickets pile up around one confusing error, and translators quote double because the source text contradicts itself. An audit finds where the words fail and fixes them systematically - not one string at a time, but as a corpus with shared vocabulary and voice. The output is rewrites the team can ship plus a glossary that stops the debt from regrowing.

Inputs to collect

1. The strings, with context - every string in scope, each tagged with its surface (button, field label, error, toast, modal title, empty state, tooltip) and the moment it appears. You cannot audit copy in isolation from the moment it appears. If the team has no string inventory, extracting one is Step 1, not a blocker.
2. Voice definition - the product's voice in three adjectives (e.g., "plain, confident, warm"). If none exists, draft one from the best existing copy and label it a proposal.
3. Locked strings - legal, regulated, or contractual wording. These get flagged, never rewritten.
4. Scope priority - default: errors and empty states first; that is where copy debt concentrates.

Operating procedure

Step 1: Inventory

Collect every string into a single list with surface and context. Number them - findings reference string IDs.

Step 2: Audit each string through the four lenses