Hire an AI copy test change recovery planner

Everything it can hand back

Your task sets the actual outputs. The specialist picks the methods that cover them.

• A timeline of each change and which test periods it splits
• A table of which groups are still fair to compare, and why the others are not
• A result table (group, period, people, conversions, rate, difference) with a supported, unclear or unusable call for each comparison
• A small copy fix for any stale fact, or a note that none is needed
• A recovery plan: resume, restart, run a new test or stop, with one thing to change, limits, an owner and a next decision date

How it does the job well

• Write for one named audience and one action. Each asset has a single job.
• Use the customer's own words from reviews, calls or surveys before inventing language.
• Every claim needs proof the business can show. Leave unproven claims out or mark them.
• Judge results against the business goal, such as profit or qualified leads, not clicks alone.

Mistakes it avoids

• Generic copy that could fit any brand.
• Comparing periods or campaigns that are not comparable, such as different dates, budgets or tracking.
• Calling a test winner before there is enough data.

What a good result looks like

An example, not your task: An offer, page, tracking rule or copy version changed while a test was running.

• Change and impact timeline. Each change with its date, the versions it touched and which test periods it splits.
• Comparability matrix. Which groups are clean to compare, which are confounded, and why.
• Observed result table. Counts and rates for valid groups, with a decision of supported, inconclusive or unusable.
• Copy patch or no-change record. A minimal fix for a stale offer or fact, or a clear note that none is needed.
• Recovery pack. Resume, restart or stop, with one variable, limits, guardrails, owner and next decision.

How the work is checked

• Every claim traces to the brand brain or supplied evidence.
• Each recommendation states the expected effect, the cost and how it will be measured.
• Copy fits the platform's length limits and the brand voice.
• States which checks passed, failed or could not run, and names missing inputs.

These checks have not been run against a model yet. Your AI uses them to check its own work.

A second opinion

Before it hands back, your AI reviews the draft the way Eugene Schwartz and Victor Schwab would. This is a way of reviewing the work. It does not mean they wrote or endorse it.

Capabilities

• Freeze the planned comparison and locate material changes. Writes down the original question, the one thing being tested, how people were split, what counts as a conversion and when the test should stop. Then it maps each change to the date it took effect and the versions it touched. The question is never rewritten after seeing results.
• Check co-changes and determine comparable units. Checks whether anything besides the copy differed between versions, such as a different offer, page or tracking. Only groups where the copy is the sole difference count as clean. Excluded rows and their totals stay visible, so nobody picks a flattering subset.
• Read only the evidence the design can support. Works out counts, rates and differences for the clean groups only, with the same dates, currency and conversion rules on both sides. A gap in rates is not proof the copy caused it. Extra digging after the fact is labelled as such, and whole-run totals stay in view.
• Repair the current copy without moving the goalposts. Fixes a stale offer or wrong fact in the copy, whatever the test says. Everything else that was agreed stays the same. If nothing is wrong, it says "no change" instead of inventing a rewrite.
• Choose and hand off the bounded recovery plan. Picks one path, resume, restart with matching versions, run a new test or stop, and writes the rules for it. How many people a new test needs depends on your starting rate and the lift worth finding, not a fixed spend or day count. The plan is handed back to you; nothing is launched.

How the role works

1. Checks your task, context and available tools.
2. Picks the methods needed and prepares a work plan.
3. Carries out supported tasks, with each method's limits and review gates.
4. Checks the real deliverables and corrects supported faults.
5. Hands back files, evidence and unresolved gaps.

Your specialist's working setup

Download the base specialist without a task form or account. README.md and SETUP.md explain how to use the folder. SOUL.md defines its scope. INTAKE.md asks missing questions inside your AI. PLAYBOOK.md, SKILLS.md, BEST_PRACTICES.md, CHECKS.md and HANDOFF.md guide the work and its checked deliverables.

Complete associated skills, supporting files and licences are included. Choose only the methods needed for the actual task. Keep context, working files and accepted feedback in your AI project.

Use this specialist through MCP or the API

Call prepare_specialist with role_id recover-a-copy-test-after-a-midrun-change only. No task is required to load it. Your AI asks what job you need done, what you want back and which relevant context it can use.

For task-led hiring, call find_specialist, explain the suggested specialists and let the user accept or change the team.

Complete ZIP: Download base specialist. API: GET /api/v1/specialists/recover-a-copy-test-after-a-midrun-change/pack. The host AI supplies its own model, tools and execution; a pack does not connect accounts or run a task.

Inputs and helpful context

The specialist starts from the task brief. Only active methods require their inputs.

For the primary method, when used

• The original test plan, with the control and variant copy, the question, how people were split and the rule for picking a winner
• Results with dates, time zone, what counts as a view and a conversion, and which ad version each row belongs to
• The dates and times when the offer, tracking, page or ads changed, plus your current approved facts such as price and terms

Tools and access

• Any good chat AI: Claude, ChatGPT and Gemini all do the sums well when the totals are pasted as a table with clear column names.
• Google Sheets: Keeps both periods side by side, so you can check any number in the report yourself.
• Any good chat AI: Listing claims and matching them to proof is text work any strong chat AI does well with this skill.
• Any good chat AI: Listing factors and mapping results is text work any strong chat AI does well with this skill.
• A spreadsheet: Keeps the held-fixed list and the results side by side for each run.

Functions and deliverables

• Copy test change recovery planner: Check a copy test after an offer or tracking change. Get a fair comparison map, clear evidence limits and a plan to restart.
  • A timeline of each change and which test periods it splits
  • A table of which groups are still fair to compare, and why the others are not
  • A result table (group, period, people, conversions, rate, difference) with a supported, unclear or unusable call for each comparison
  • A small copy fix for any stale fact, or a note that none is needed
  • A recovery plan: resume, restart, run a new test or stop, with one thing to change, limits, an owner and a next decision date
• Campaign change impact reviewer: Map which campaign assets break when an approved price, offer or claim changes. Get a repair order and release limits from your own files.
  • A list of each asset showing if it is affected, unaffected, unclear or not checked
  • The exact place where each old fact appears, including derived values
  • A repair order with the smallest edit, owner and check for each fix
  • A date line that keeps old and new results apart
  • A list of assets and approvals still missing
• Ad variant change auditor: Check your control ad and variants against the test you planned. Find hidden changes and get the smallest fixes before you launch an ad test.
  • A list of every change between the control and each variant
  • A label on each change: planned, unplanned or could not check
  • A ready or not-ready verdict for each variant
  • The smallest fix for each problem, such as undoing a change or splitting it into its own test
  • A list of what is still unknown
• Ad results report writer: Paste two periods of ad totals. Get the one-line answer, what changed and three ranked actions.
  • A coverage line saying what the report includes and what's missing
  • The answer in one line, at the top
  • A table of the main numbers, this period against last, with the change
  • Two to four changes that matter, one unresolved worry, and three ranked actions, with budget changes marked for approval
  • Any of its own checks the report still misses, each named
• Claim evidence checker: Share your copy and evidence. See which claims are supported, which go too far and how to fix them.
  • Unique stated and implied claims, with proof or a gap flag
  • Evidence scope, dates, quote permissions and claim-by-claim findings
  • An evidence-match score with evaluated/total coverage
  • A fix for each gap and any separate rule checks still needed
• One-change experiment planner: Plan a one-change experiment. Tell it what you want to learn and get a test plan that changes one thing and says what each result means.
  • The question rewritten in plain terms, with each term defined
  • The one change to test and the list of things held fixed
  • A second check, the no-effect result and what each outcome means
• Brand profile builder: Share your website. Get a reusable profile covering your products, customers, voice and approved claims, with sources.
  • A folder of eight plain files, from a start file for your AI to a claims list and a change log
  • A tag on every fact, and every claim marked approved, pending or banned
  • A two-sentence diagnosis of your biggest gap, and a list of what's missing and who can answer it
  • A short slice for your next step, if you name one
• Eugene Schwartz: Match a headline or sales page to what buyers already want and know. Apply Eugene Schwartz’s recorded approach to research, claims and proof.
  • Your problem worked on the way Eugene Schwartz would: their questions, their method, their push-back
  • The answer or the work, in Eugene Schwartz's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step
• Victor Schwab: Review ad headlines and openings using Victor Schwab’s recorded approach. Name the reader, support the promise and plan how to track responses.
  • Your problem worked on the way Victor Schwab would: their questions, their method, their push-back
  • The answer or the work, in Victor Schwab's voice, using their ideas by name
  • Anything that goes beyond their public record, marked
  • One suggested next step

Tasks you can use it for

• An offer, page, tracking rule or copy version changed while a test was running.
• You need to know which comparisons remain usable before rewriting an apparent winner.

Limits to check before starting

• You are planning a new copy test: use the Cross-over copy test planner.
• Nothing changed during the test and you only want to read the result: use the A/B test results reader.
• You want to pick the next idea to test from scratch: use the One-change experiment planner.

Best way to use this role

Give it one clear outcome, the actual files and a definition of done. Keep the work in one AI project so it can reuse checked context and earlier files.

• Download the pack and add it to your AI, or paste the instructions into a chat.
• Attach the test plan, your results export and the change log. Say which approved facts are current.
• When the AI pastes back a stage, check it before the next one starts. In a plain chat, paste each stage's result into the next prompt if the AI loses track.
• Before you act on the recovery plan, check the result table against your own export.

Read it as data

Read the complete role setup as JSON. Connect your AI to the AI Blocks MCP library and read aiblocks://roles/recover-a-copy-test-after-a-midrun-change for its role instructions and pinned sources.

This is a prepared AI role. No task has run. Your AI carries out authorized work using its available tools and reports the actual deliverables and checks.