Compare Two Texts
Drop two pieces of text side by side and get the literal difference between them — what was added, removed, and reworded.
The changes you would miss on a re-read — an added word, a swapped term — surfaced exactly, so nothing slips past.
The most dangerous edits are the small ones: a single inserted word that changes a meaning, a quietly swapped term. This loads two near-identical sentences with exactly those subtle differences and surfaces them, word by word. Re-reading misses them because the brain fills in what it expects; a diff does not. It marks precisely what differs and leaves the significance to you — its job is to make sure nothing slips past unnoticed.
Paste the near-identical texts
Two versions that look almost the same.
Surface the subtle changes
A single added word or swapped term, marked exactly.
Miss nothing
The diff catches what a re-read glosses over.
It won't — it marks what changed and leaves the significance to you. The NOTE says so: "This is a mechanical diff: it shows what changed, not what it means or which text is better." The report surfaces an inserted word ("Friday" becoming "Friday afternoon") in MODIFIED CONTENT and UNIFIED DIFF. For whether a revision improved things it points to the Prompt Version Diff.
The Mode is Mixed (line + word), so it reports word counts and pins the exact change. In the sample, "runbook" becoming "shared runbook" shows as a MODIFIED CONTENT pair and a +/- line in the UNIFIED DIFF, and STATISTICS tallies "+3 / -1 words." Re-reading misses it because the brain fills in expected text; the diff marks precisely what differs so nothing slips past.
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.