See how it works — then open one and try.
Two live demos you can open in one click, the guides behind them, and the long-form field manual for giving Claude, ChatGPT, Cursor, or Gemini precise feedback. Read in any order — each piece stands alone. If you want the shorter read on which tool to pick, the manifesto is it. Or subscribe via RSS →
Fix an answer you got
Five things wrong, one anchored paste — instead of giving up at fix three. Opens a real answer, already marked up with comments.
Open it in the app Live demoReset the question first
Answer the model's open decisions up front — so the first draft comes back right. Opens a real questionnaire, ready to fill in.
Open it in the appPassbackAI now lives inside Claude, ChatGPT, Gemini, and Perplexity
The PassbackAI Chrome extension intercepts Copy on any of the four and shows a toast. One click forwards the answer to passbackai.com pre-loaded. Six steps become one. No backend, no telemetry.
The Guide · Start hereHow to give Claude or ChatGPT feedback on 5 things at once
The paired-passage pattern — a manual recipe you can run in any plain-text editor, and the mechanism for why structured input beats prose every time.
How do you share a doc when nobody has an account?
No server, no logins — and a Share button anyway. The link doesn't point at your document; it is your document, riding in the part of a URL the browser never sends anywhere. Optional password makes it end-to-end encrypted.
Every incomplete AI review costs you another generation
Reviewing a long answer is so expensive in a chat box that you skim once and skip half the fixes — and every fix you skip comes back as another full generation. Make the read cheap and one pass replaces three.
Why typing feedback to the AI stops working at five corrections
The chat box doesn't fail at five. It fails at three. By point four you're shipping a message you already know the model will mis-target — and the fifth correction lives its entire life inside your head.
Why ChatGPT rewrites the whole document when you only asked for one fix
The chat box has no target selection. RLHF trained the model to return complete documents. Four prompt attempts that almost work, one format that does.
A prompt that gets Claude to only edit the passages you named
Every "only edit X" variant ranked by reliability, with copy-pasteable templates for Claude, ChatGPT, Cursor, and Gemini — plus a system-prompt rule for API and Project users.
Claude Projects vs attaching a doc: which actually keeps your edits scoped?
Projects solves persistence. Attachments solve freshness. Neither solves scoping — the thing you actually wanted. Plus notes on NotebookLM, Canvas, and Gemini Files.
How to give Cursor feedback on a long Markdown file
Cursor edits prose like code: broadens context, applies a coherent diff, regenerates the neighborhood. Composer vs Agent vs chat, with a .cursorrules recipe that makes scoped edits the default.
How to add comments to a Markdown file (2026 edition)
Every practical method — HTML comments, Google Docs, Notion, GitHub PR, Slack, purpose-built comment layers — ranked, with the 2026 case the old methods don't cover.
So much of what we read now is AI text with a short shelf-life — useful for one session, then gone. I wanted a faster, sharper way to work on it — and not alone.
So: mark what's wrong, keep your last 20 a click away, and when you want another set of eyes, hand the whole thing off as one link — your comments ride along inside it. Nothing is ever uploaded; it all stays on your device.
Made by Elad · LinkedIn
Read the full story →