Privacy policies read by 5% of users protect 0% — they look thorough but communicate nothing. A good plain-English rewrite preserves the legal claim while making it readable; lawyers re-check the legal bits separately.
Who this is for
Founders trying to make their policies feel less hostile, comms leads paired with legal, indie devs writing first-version privacy / TOS.
When not to use these prompts
Don’t use these as final legal copy — always have counsel sign off. Don’t use them to weaken protections users need.
Prompt anatomy / structure formula
Every policy rewrite prompt should carry six elements:
- Audience: one specific reader.
- Goal: one outcome — read / click / agree / share.
- Voice: 2-3 anchor adjectives.
- Constraints: word count, banned phrases, must-include facts.
- Format: paragraph, bulleted, headed, table.
- Examples: 1-2 tone samples — best lever for matching voice.
Best for
- Privacy policy plain-English rewrite
- Terms of service rewrite
- Cookie banner / consent copy
- Acceptable use policy
- Data subject request reply templates
12 copy-ready prompt templates
1. Plain-English rewrite preserving claims
Rewrite this section of our policy in 7th-grade English. Constraint: preserve every legal claim, do not weaken or expand. Output a side-by-side: legal version | plain-English version. Mark any plain-English line where meaning may have shifted for legal review.2. Top-of-page TL;DR
Write a 3-bullet "what this policy says" at the top of the page. Each bullet ≤ 20 words. Plain English, no jargon. Add a "Read the full policy if you want detail" link to the legal text below.3. Privacy: what we collect
Rewrite the "data we collect" section as a table: data type | why we collect it | how long we keep it | who we share it with. Skip categories we don't actually collect.4. Privacy: rights you have
Plain-English rewrite of user rights: access, correct, delete, export, restrict, object, withdraw consent. Each: one sentence what + one sentence how. Don't use legal verbs ("hereinafter", "shall").5. Cookie banner copy
Write cookie banner copy: (1) ≤ 40-word notice, (2) Two clear buttons (Accept / Reject), (3) "Manage preferences" link to category-by-category toggle. Skip dark patterns — Reject must be as visible as Accept.6. Terms: liability + indemnity in plain language
Rewrite our liability + indemnity section in plain English without weakening protections. Goal: a user can read it and understand "what could happen if this product breaks". Keep the legal version below for counsel.7. Acceptable use policy
Write an Acceptable Use Policy as a list of "you may not": specific behaviours, not vague categories. Examples: spam, scrape APIs without permission, harass users, evade rate limits. Each item: 1-line behaviour + 1-line consequence.8. Data subject request reply
Draft reply templates for: (1) Access request, (2) Deletion request, (3) Correction request, (4) Export request, (5) Objection / withdrawal. Each: acknowledge in 24h, action timeline, what we need to verify identity, what they'll receive.9. Children’s privacy
Plain-English children's privacy section. Cover: minimum age, no targeted ads, parental rights, how to delete a child's data. Don't bury behind "We do not knowingly…" — say what you do, not just what you don't.10. International transfer plain-English
Rewrite the international data transfer section: (1) Where data goes, (2) Legal basis (SCCs, Adequacy decision), (3) What protections, (4) How a user gets a copy of the safeguards. Don't reduce to "We comply with applicable laws."11. Plain-English consent UX
For our consent UI, write 3 variants of consent copy: (a) base case, (b) re-confirmation after policy change, (c) granular toggles. Each ≤ 60 words. The "Reject all" must be one click.12. Policy diff for users
Our policy changed. Write a user-facing summary of the changes: (1) What changed, (2) Why, (3) What you should do (if anything), (4) Effective date. Plain English. Skip a full redline — link to it.Common mistakes
- Vague audience — output reads generic.
- No tone anchor — every variant comes back same flavour.
- No constraints — word count, banned phrases, length cap.
- Skipping examples — examples are the strongest signal for voice.
- Trusting first draft — AI lands on safe middle.
- Overusing AI clichés (“In today’s fast-paced…”).
- No fact-check pass — AI is confidently wrong sometimes.
- Reducing meaning while rewriting — must have legal re-check.
How to push results further
- Give 1-2 tone examples; “be friendly” is noise.
- Constrain ruthlessly.
- Read aloud before publishing.
- Cut adverbs / adjectives that don’t carry weight.
- AI for drafts 1-2, human edit for 3 — and 3 is what ships.
- Anchor in a real person from your audience.
- Test the headline standalone.
- Always preserve a side-by-side: rewrite | legal. Lawyer reviews the rewrite.
Practical depth notes
Use these prompts as starting points, not final answers. For Policy & Terms Plain-English Rewrite Prompts, the useful extra work is to replace every generic placeholder with a real constraint: audience, channel, length, brand voice, examples to imitate, and examples to avoid. Run at least two versions with different constraints, then compare the outputs side by side instead of accepting the first polished response.
A good result should pass three checks: it is specific enough that another person could reuse it, it avoids vague praise or filler, and it gives you an editable artifact rather than a broad suggestion. If the output feels generic, add one concrete reference, one forbidden pattern, and one measurable success criterion before rerunning the prompt. Before saving a prompt as reusable, test it on one realistic input and one edge case. The realistic input proves the template can produce the normal deliverable; the edge case shows whether it handles messy constraints, missing context, or an unusual audience. Keep the better output, but also keep the failed version with a note on what was missing. That small failure log is what turns a prompt collection from a list of nice sentences into a practical working library.
FAQ
- How long should this piece be?: Match the channel — shorter where attention is shorter.
- Can AI do the whole draft?: AI for first two passes, human for the third.
- How often refresh?: When audience or claims change, or quarterly for evergreen content.
- Should I publish without an edit pass?: No. AI is confident, not always correct.
- Single voice or per-channel?: One brand voice; channels shift tone axes within voice.
- Repurpose this prompt for other content types?: Yes — swap audience, goal, voice. Structure is reusable.