Choose one of three approaches. The steps for that option appear below.
Choose an option above. On a phone, swipe the tabs left or right to see all options →
ChatGPT proposes the promise-continuity table, drafts the conversion review and cross-checks it. You check both gates and decide.
Assemble the materials
Build continuity table
Check the table
Draft and cross-check
Check and decide
Use: You
Assemble the ad and email claims, current landing-page copy and approved offer terms, retaining authorised source IDs and dates.
Check each item is the approved version, dated and permitted; list anything missing as still to confirm.
Use: ChatGPT
Ask ChatGPT for a promise-continuity table identifying omissions, contradictions and unsupported expectations, with source references and uncertain facts.
What to paste into the tool
Task: Promise-continuity table identifying omissions, contradictions and unsupported expectations; source references; uncertain or absent facts; Source packet: Ad and email claims, current landing-page copy and approved offer terms. Use only the supplied packet. Build a labeled table with source IDs, dates, uncertainty and permitted-use limits on each row. Check acquisition claims, supplied landing-page copy and approved offer terms side by side; record omissions, contradictions and unsupported expectations. Retain the source packet as an unchanged attachment in the output bundle. Keep unresolved facts and approval dependencies explicit. Do not resolve a missing fact by inventing one. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign
Use: You
Compare every table row with the source materials and correct it; resolve or retain missing facts before drafting.
Check the claims, page copy and offer terms side by side; record omissions, contradictions and unsupported expectations.
Use: ChatGPT
Ask ChatGPT to draft corrections for the omissions and contradictions, then cross-check the draft against the checked table and correct it.
What to paste into the tool
Task: Draft conversion review with claim corrections and destination gaps; Open questions and approval dependencies retained beside the recommendations; Reviewer-checked promise-continuity table identifying omissions, contradictions and unsupported expectations; source references; uncertain or absent facts; Supplied constraints, retained open questions and approval dependencies with source IDs and dates; Source packet: Ad and email claims, current landing-page copy and approved offer terms. Identify omissions, contradictions and unsupported expectations, then propose corrections that restore approved promises without adding persuasion claims. Retain the checked table, constraints and source packet unchanged in the output bundle. Keep unresolved facts and approval dependencies explicit. Do not resolve a missing fact by inventing one. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign. Second message, after your check: Task: Corrected draft with a change list and unresolved mismatches flagged for the reviewer. Compare the draft with the checked promise-continuity table and the retained source packet. Correct every mismatch you find in the draft, keep source IDs, dates, uncertainty and named exceptions, and list each change. Flag anything you cannot settle from the supplied material; do not invent facts, figures, policies or claims. Return preparation material only; publishing, outreach, audience changes, tracking deployment and financial commitments are outside this task.
Use: You
Compare the corrected draft and change list with the checked table, confirm the named exceptions, then decide; publishing stays outside.
Check each correction restores an approved promise and adds no unsupported persuasion claims. If a check fails, correct the draft or leave the workflow incomplete.
Claude proposes the promise-continuity table, drafts the conversion review and cross-checks it. You check both gates and decide.
Assemble the materials
Build continuity table
Check the table
Draft and cross-check
Check and decide
Use: You
Assemble the ad and email claims, current landing-page copy and approved offer terms, retaining authorised source IDs and dates.
Check each item is the approved version, dated and permitted; list anything missing as still to confirm.
Use: Claude
Ask Claude for a promise-continuity table identifying omissions, contradictions and unsupported expectations, with source references and uncertain facts.
What to paste into the tool
Task: Promise-continuity table identifying omissions, contradictions and unsupported expectations; source references; uncertain or absent facts; Source packet: Ad and email claims, current landing-page copy and approved offer terms. Use only the supplied packet. Build a labeled table with source IDs, dates, uncertainty and permitted-use limits on each row. Check acquisition claims, supplied landing-page copy and approved offer terms side by side; record omissions, contradictions and unsupported expectations. Retain the source packet as an unchanged attachment in the output bundle. Keep unresolved facts and approval dependencies explicit. Do not resolve a missing fact by inventing one. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign
Use: You
Compare every table row with the source materials and correct it; resolve or retain missing facts before drafting.
Check the claims, page copy and offer terms side by side; record omissions, contradictions and unsupported expectations.
Use: Claude
Ask Claude to draft corrections for the omissions and contradictions, then cross-check the draft against the checked table and correct it.
What to paste into the tool
Task: Draft conversion review with claim corrections and destination gaps; Open questions and approval dependencies retained beside the recommendations; Reviewer-checked promise-continuity table identifying omissions, contradictions and unsupported expectations; source references; uncertain or absent facts; Supplied constraints, retained open questions and approval dependencies with source IDs and dates; Source packet: Ad and email claims, current landing-page copy and approved offer terms. Identify omissions, contradictions and unsupported expectations, then propose corrections that restore approved promises without adding persuasion claims. Retain the checked table, constraints and source packet unchanged in the output bundle. Keep unresolved facts and approval dependencies explicit. Do not resolve a missing fact by inventing one. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign. Second message, after your check: Task: Corrected draft with a change list and unresolved mismatches flagged for the reviewer. Compare the draft with the checked promise-continuity table and the retained source packet. Correct every mismatch you find in the draft, keep source IDs, dates, uncertainty and named exceptions, and list each change. Flag anything you cannot settle from the supplied material; do not invent facts, figures, policies or claims. Return preparation material only; publishing, outreach, audience changes, tracking deployment and financial commitments are outside this task.
Use: You
Compare the corrected draft and change list with the checked table, confirm the named exceptions, then decide; publishing stays outside.
Check each correction restores an approved promise and adds no unsupported persuasion claims. If a check fails, correct the draft or leave the workflow incomplete.
You build the continuity table and write the corrections. Perplexity critiques the draft; you accept or reject each item.
Build the review
Critique the draft
Decide each item
Use: You
Assemble the claims, page copy and offer terms; build the promise-continuity table locally and write proposed corrections and destination gaps.
Check items are dated and permitted; compare claims, page copy and offer terms; record omissions, contradictions and unsupported expectations.
Use: Perplexity
Ask Perplexity document chat to critique your draft against the supplied materials, without adding live-web inputs.
What to paste into the tool
Task: Discrepancy critique of the human-drafted conversion review with source-row locators and open questions; Human-checked promise-continuity table identifying omissions, contradictions and unsupported expectations; source references; uncertain or absent facts; Supplied constraints, retained items still to confirm and approval dependencies with source IDs and dates; Source packet: Ad and email claims, current landing-page copy and approved offer terms; Human-drafted conversion review with proposed claim corrections, destination gaps and retained evidence questions. Compare the human-drafted review with the checked continuity table and supplied evidence. Identify proposed corrections that lack an approved term, missing destination gaps, changed qualifiers and uncertain source links. Point to supplied row IDs. Use only supplied material; do not search the web, infer a live URL or present this as a current-page audit. Retain the checked table, human draft or brief, constraints and source packet unchanged in the output bundle. Keep unresolved facts and approval dependencies explicit. Do not resolve an open fact by inventing a fact. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign
Use: You
Check each critique item against the supplied copy and approved terms, accept or reject it, and assemble the reviewed conversion review; publishing stays outside.
Check each correction restores an approved promise and adds no unsupported persuasion claims. If a check fails, correct the draft or leave the workflow incomplete.
Best when: You want AI proposals for table, review and a first cross-check
What it does: ChatGPT proposes, drafts and cross-checks; you check both gates
Strong at: Analyses uploaded files; writes and rewrites text
Limit: A table error can reach the review; check at the checkpoint
Free plan: Yes, limited (file upload and analysis caps)
Best when: You want AI proposals for table, review and a first cross-check
What it does: Claude proposes, drafts and cross-checks; you check both gates
Strong at: Drafts and edits text in many formats
Limit: Usage capped in 5-hour and weekly windows
Free plan: Yes, limited (5-hour and weekly usage caps)
Best when: You author the corrections; AI adds a critique as extra review
What it does: Perplexity critiques your draft; you build the table and decide
Strong at: The AI critiques your draft rather than choosing the correction
Limit: The critique can miss a gap or suggest an unsupported correction
Free plan: Yes, limited (uploads capped at 40 MB per file)
Before you paste into any AI tool, remove any confidential information. Put it back at the end.
Deciding between ChatGPT and Claude for this? See the comparison.
The named reviewer compares working records and final drafts against retained source evidence; unresolved questions stay visible.
These are proposed preparation workflows; execution, publication, sending, deployment, account changes and spending are outside scope.
Check the result against your original inputs. Approve it before sharing or acting.