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 →
Gemini proposes the readiness register, then drafts the go-or-hold checklist. You check each against the evidence and decide.
Assemble the materials
Build readiness register
Check every row
Draft the checklist
Check and decide
Use: You
Assemble the approved brief, asset inventory, owner list and proposed launch window, retaining authorised source IDs and dates.
Check each item is the approved version, dated and permitted; list anything missing as still to confirm.
Use: Gemini
Ask Gemini for a readiness register linking each promise to assets, approvals and unresolved dependencies, with source references and uncertain facts.
What to paste into the tool
Task: Readiness register linking each promise to assets, approvals and unresolved dependencies; source references; uncertain or absent facts; Source packet: Approved brief, asset inventory, owner list and proposed launch window. Use only the supplied packet. Build a labeled table with source IDs, dates, uncertainty and permitted-use limits on each row. Check each promise, asset, owner role, approval and dependency against the brief and asset inventory. 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 Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign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 register row with the source materials and correct it; resolve or retain missing facts before drafting.
Check each promise, asset, owner role, approval and dependency against the brief and asset inventory.
Use: Gemini
Ask Gemini to assess asset and approval evidence against launch-critical dependencies and draft the checklist, open questions beside each item.
What to paste into the tool
Task: Draft go-or-hold checklist for a human launch decision; Open questions and approval dependencies retained beside the recommendations; Reviewer-checked readiness register linking each promise to assets, approvals and unresolved dependencies; source references; uncertain or absent facts; Supplied constraints, retained items still to confirm and approval dependencies with source IDs and dates; Source packet: Approved brief, asset inventory, owner list and proposed launch window. List each launch-critical dependency with readiness evidence or an explicit blocker; retain owner roles, asset links, approvals and the proposed launch window as supplied; do not deploy. 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 checklist with open questions and approval dependencies beside each item. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign
Use: You
Check each checklist item against the register and source materials, then decide; launching stays outside this workflow.
Check every launch-critical dependency has readiness evidence or an explicit blocker, and no deployment occurs. If a check fails, send the checklist back for redrafting or leave the workflow incomplete.
ChatGPT proposes the readiness register, then drafts the go-or-hold checklist. You check each against the evidence and decide.
Assemble the materials
Build readiness register
Check every row
Draft the checklist
Check and decide
Use: You
Assemble the approved brief, asset inventory, owner list and proposed launch window, 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 readiness register linking each promise to assets, approvals and unresolved dependencies, with source references and uncertain facts.
What to paste into the tool
Task: Readiness register linking each promise to assets, approvals and unresolved dependencies; source references; uncertain or absent facts; Source packet: Approved brief, asset inventory, owner list and proposed launch window. Use only the supplied packet. Build a labeled table with source IDs, dates, uncertainty and permitted-use limits on each row. Check each promise, asset, owner role, approval and dependency against the brief and asset inventory. 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 register row with the source materials and correct it; resolve or retain missing facts before drafting.
Check each promise, asset, owner role, approval and dependency against the brief and asset inventory.
Use: ChatGPT
Ask ChatGPT to assess asset and approval evidence against launch-critical dependencies and draft the checklist, open questions beside each item.
What to paste into the tool
Task: Draft go-or-hold checklist for a human launch decision; Open questions and approval dependencies retained beside the recommendations; Reviewer-checked readiness register linking each promise to assets, approvals and unresolved dependencies; source references; uncertain or absent facts; Supplied constraints, retained items still to confirm and approval dependencies with source IDs and dates; Source packet: Approved brief, asset inventory, owner list and proposed launch window. List each launch-critical dependency with readiness evidence or an explicit blocker; retain owner roles, asset links, approvals and the proposed launch window as supplied; do not deploy. 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 checklist with open questions and approval dependencies beside each item. Produce a draft only; do not publish, send, deploy, change accounts, spend or launch a campaign
Use: You
Check each checklist item against the register and source materials, then decide; launching stays outside this workflow.
Check every launch-critical dependency has readiness evidence or an explicit blocker, and no deployment occurs. If a check fails, send the checklist back for redrafting or leave the workflow incomplete.
You build the register by hand; Coda critiques gaps. No job is submitted, content published or campaign executed.
Build the register
Critique evidence gaps
Write the checklist
Use: You
Assemble the approved brief, asset inventory, owner list and launch window; build a readiness register grouped by owner role from the supplied evidence.
Check materials are dated and permitted, and each promise, asset, owner role, approval and dependency matches the brief and inventory.
Use: Coda
Paste the checked register into a Coda doc and ask for an evidence-gap critique by owner role.
What to paste into the tool
Task: Draft evidence-gap critique grouped by owner role with absent approval links and unresolved dependency questions; Human-checked readiness register linking each promise to assets, approvals and unresolved dependencies; source references; uncertain or absent facts; Supplied constraints, retained items still to confirm and approval dependencies with source IDs and dates; Source packet: Approved brief, asset inventory, owner list and proposed launch window; Freshly private readiness table grouped by owner role, with supplied evidence links, proposed window and flagged approval gaps. Identify rows with absent asset, approval or dependency evidence, grouped by supplied owner role. Point to the supplied row IDs and list unresolved questions; do not decide go or hold or change table data. 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 the critique against each owner-role row and supplied evidence, then write the go-or-hold checklist; approval and execution stay separate.
Check each checklist item against the owner-role rows and supplied evidence. If a check fails, correct the draft or leave the workflow incomplete.
Best when: You want AI proposals for register and checklist with a check between
What it does: Gemini proposes the register and checklist; you check and decide
Strong at: Drafts and summarises text; finds info in Gmail and Drive
Limit: A register error can reach the checklist; check each row first
Free plan: Yes, limited
Best when: You want AI proposals for register and checklist with a check between
What it does: ChatGPT proposes the register and checklist; 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: You want to write the checklist after an in-doc gap critique
What it does: Coda critiques gaps; you build the register and write the checklist
Strong at: Docs with tables that sync like databases
Limit: The AI critique does not establish readiness; check every statement
Free plan: Yes, limited (attachments capped at 1 GB per doc)
Before you paste into any AI tool, remove any confidential information. Put it back at the end.
Deciding between ChatGPT and Gemini 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.