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 →
Claude proposes the source-to-local meaning table, then drafts the local brief. You check each against the evidence and decide.
Assemble the materials
Build meaning table
Check every row
Draft the brief
Check and decide
Use: You
Assemble the approved source campaign, local-language research and substantiation allowed in the target market, retaining authorised source IDs and dates.
Check each item is permitted for this campaign and approved; list anything missing as still to confirm.
Use: Claude
Ask Claude for a source-to-local meaning table with cultural assumptions and unsupported local proof, plus source references and uncertain facts.
What to paste into the tool
Task: Source-to-local meaning table with cultural assumptions and unsupported local proof; source references; uncertain or absent facts; Source packet: Approved source campaign, local-language research and substantiation allowed in target market. Use only the supplied packet. Build a labeled table with source IDs, dates, uncertainty and permitted-use limits on each row. Check each local interpretation and cultural assumption against local-language research and permitted target-market substantiation. Retain the source packet as an unchanged attachment 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 Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign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
Compare every table row with the source materials and correct it; resolve or retain missing facts before drafting.
Check each local interpretation and cultural assumption against the local-language research and permitted substantiation.
Use: Claude
Ask Claude to adapt the campaign meaning to the documented local context, keeping substantiation and open cultural assumptions, reviewer questions beside each.
What to paste into the tool
Task: Draft local campaign message brief with proposed adaptations and reviewer questions; Open questions and approval dependencies retained beside the recommendations; Reviewer-checked source-to-local meaning table with cultural assumptions and unsupported local proof; source references; uncertain or absent facts; Supplied constraints, retained items still to confirm and approval dependencies with source IDs and dates; Source packet: Approved source campaign, local-language research and substantiation allowed in target market. Draft proposed adaptations tied to documented local audience meaning; retain substantiation limits, cultural assumptions and reviewer questions; do not infer market usability or legal approval. Retain the checked table, 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. Assemble the review-ready brief with reviewer questions beside each proposed adaptation. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign
Use: You
Check each adaptation against the checked table and source materials, then decide; publishing and financial commitments need separate human authority.
Check local changes answer evidenced context and no market usability or legal approval is inferred. If a check fails, send the brief back for redrafting or leave the workflow incomplete.
ChatGPT proposes the source-to-local meaning table, then drafts the local brief. You check each against the evidence and decide.
Assemble the materials
Build meaning table
Check every row
Draft the brief
Check and decide
Use: You
Assemble the approved source campaign, local-language research and substantiation allowed in the target market, retaining authorised source IDs and dates.
Check each item is permitted for this campaign and approved; list anything missing as still to confirm.
Use: ChatGPT
Ask ChatGPT for a source-to-local meaning table with cultural assumptions and unsupported local proof, plus source references and uncertain facts.
What to paste into the tool
Task: Source-to-local meaning table with cultural assumptions and unsupported local proof; source references; uncertain or absent facts; Source packet: Approved source campaign, local-language research and substantiation allowed in target market. Use only the supplied packet. Build a labeled table with source IDs, dates, uncertainty and permitted-use limits on each row. Check each local interpretation and cultural assumption against local-language research and permitted target-market substantiation. Retain the source packet as an unchanged attachment 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
Compare every table row with the source materials and correct it; resolve or retain missing facts before drafting.
Check each local interpretation and cultural assumption against the local-language research and permitted substantiation.
Use: ChatGPT
Ask ChatGPT to adapt the campaign meaning to the documented local context, keeping substantiation and open cultural assumptions, reviewer questions beside each.
What to paste into the tool
Task: Draft local campaign message brief with proposed adaptations and reviewer questions; Open questions and approval dependencies retained beside the recommendations; Reviewer-checked source-to-local meaning table with cultural assumptions and unsupported local proof; source references; uncertain or absent facts; Supplied constraints, retained items still to confirm and approval dependencies with source IDs and dates; Source packet: Approved source campaign, local-language research and substantiation allowed in target market. Draft proposed adaptations tied to documented local audience meaning; retain substantiation limits, cultural assumptions and reviewer questions; do not infer market usability or legal approval. Retain the checked table, 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. Assemble the review-ready brief with reviewer questions beside each proposed adaptation. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign
Use: You
Check each adaptation against the checked table and source materials, then decide; publishing and financial commitments need separate human authority.
Check local changes answer evidenced context and no market usability or legal approval is inferred. If a check fails, send the brief back for redrafting or leave the workflow incomplete.
ChatGPT drafts the meaning table and adaptations. QuillBot rewords only selected checked sentences. You approve.
Assemble the materials
Draft the brief
Check the draft
Reword selected sentences
Approve or hold
Use: You
Assemble the approved source campaign facts, local-language research and allowed substantiation, keeping the original sentence IDs.
Check only information permitted for this campaign is used, with no inferred protected or sensitive traits.
Use: ChatGPT
Paste the materials and ask ChatGPT for the draft local brief: meaning table, adaptations with local evidence, open cultural and reviewer questions.
What to paste into the tool
Task: Draft a local campaign message brief from the packet I paste. Parts: a source-to-local meaning table; proposed adaptations, each with its local evidence; unresolved cultural assumptions as open questions; reviewer questions. Keep source IDs and dates next to each item. Regional observations are notes only, never usability claims or exclusions. Use only the supplied packet; missing facts stay marked as missing. Draft only: no publishing, outreach, audience changes, tracking or spending. Packet: [paste the packet].
Use: You
Check every adaptation, local claim, source ID and date against the original materials.
Check each adaptation traces to supplied or explicitly sourced evidence with its ID and date; the brief stays a draft.
Use: QuillBot
Ask QuillBot for wording alternatives on selected checked sentences, keeping the original sentence IDs.
What to paste into the tool
Task: Alternative wording for selected checked-brief sentences with their original sentence IDs. Rephrase only the selected sentences for readability while preserving the supplied meaning, qualifiers and open questions. Keep the original sentence ID next to each alternative. Do not make local evidence claims. Sentences: [paste the selected checked sentences with their IDs].
Use: You
Accept or reject each wording alternative, edit, and approve the reviewed draft.
Check meaning and substantiation stay intact after each accepted alternative; no publishing, outreach, audience changes, tracking deployment or financial commitments without separate human authority.
Best when: You want AI proposals for table and draft with a check between
What it does: Claude proposes the table and drafts; you check and decide
Strong at: Drafts and edits text in many formats
Limit: A table error can reach the draft; check each row first
Free plan: Yes, limited (5-hour and weekly usage caps)
Best when: You want AI proposals for table and draft with a check between
What it does: ChatGPT proposes the table and drafts; you check and decide
Strong at: Analyses uploaded files; writes and rewrites text
Limit: Free plan limits file uploads, voice and data analysis
Free plan: Yes, limited (file upload and analysis caps)
Best when: Assistant drafts; a wording tool rewords only selected sentences
What it does: ChatGPT drafts, QuillBot rewords; you check every claim
Strong at: Wording alternatives stay mapped to the original sentence IDs
Limit: A rephrased sentence can change a qualifier; compare every change
Free plan: ChatGPT: Yes, limited (upload caps); QuillBot: Yes, limited (125 words)
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.