Compare Two Texts
Drop two pieces of text side by side and get the literal difference between them — what was added, removed, and reworded.
When the edits are inside a sentence, line mode is too coarse. Word mode highlights the exact words inserted and deleted.
Reword a sentence and a line diff calls the whole line changed, which tells you nothing about what actually moved. This loads two versions of one sentence and runs a word-level diff, marking each swapped word inline — quick to fast, jumps to leaps, lazy to sleeping. Word mode is for prose where the line break is irrelevant and the change lives inside the words. It pinpoints the edits without claiming the rewrite reads better; that judgment is yours.
Paste the two sentences
Two versions of a reworded line or paragraph.
Switch to word mode
Highlights changed words inside the line.
See each swap
Every inserted and deleted word marked inline.
It sets Mode to Word (word-by-word) and rewrites the sentence as one UNIFIED DIFF line, wrapping each deletion in [-...-] and each insertion in {+...+} right where it occurred, so quick becomes [-quick-] {+fast+} and jumps becomes [-jumps-] {+leaps+}. You see the four swaps inline instead of one whole-line replacement.
Use word mode when the change lives inside a sentence and the line break is irrelevant, so a line diff would flag the whole line as 1 changed and tell you nothing. The report keeps Lines: 0 added, 0 removed, 1 changed but breaks it down to +4 / -4 words in STATISTICS. For line-structured data, line mode is cleaner.
It cannot; the NOTE states this is a mechanical diff showing what changed, not what it means or which text is better. It marks lazy as [-lazy-] {+sleeping+} without claiming sleeping reads better. For whether a revision is an improvement or regression, the NOTE points to Prompt Version Diff; for which of two prompts wins, to Prompt Comparator.
Drop two pieces of text side by side and get the literal difference between them — what was added, removed, and reworded.
Paste two texts and see exactly what changed — a git-style colored diff with additions, deletions, and word-level edits, and a mechanical change count.
Make sure a fix didn't break three other things — compare an agent's outputs across two versions on the same scenarios and flag every behavior that changed for the worse.
See exactly what changed between v1 and v2 of a prompt — added, removed, and modified instructions, plus whether the revision reduced or introduced risk.
A side-by-side way to decide between two ChatGPT prompt drafts — scored on clarity, specificity, output control, and risk instead of gut feeling.
Paste any text and see characters, words, lines, and reading time at once — plus whether it fits Twitter, SMS, and meta-description limits.
See exactly what changed between two texts — a git-style colored diff with added, removed, and word-level edits. Mechanical, no judgment.