AI Blocks › Plan what ads to test
A fair test of two ads, and a plain call on which one won
Give it two ads. Get a fair split-run test, a reply offer that brings enough replies and a read of the result.
Test two ads head to head and read the winner is a free AI workflow for the job "Plan what ads to test". It guides your AI through several skills in order, passing each step's output to the next.
Free · No account · Made by AI Blocks · Thinking: high
What it does
Most tests of two ads are not fair. One ran on a Monday and the other in a quiet week. One sat at the top of the page. When a gap shows up, nobody can say whether the ad caused it. Then a small gap gets called a win, and the result is luck. This workflow plans the test so only the thing you changed can explain a gap. Both versions go out at the same time to matched halves of the same audience, each with its own code. It picks a small reply offer, the same in both, and checks it will bring about a hundred replies a version without drawing people who only want something free. You run the test and count the replies. Then it states the gap as a percentage, checks it against luck, follows replies through to sales and cost, and gives a plain call.…
You give it
- The two versions of the ad, email or page
- Your offer and what a reply means (optional)
- Your product facts, so a reply item can be chosen (optional)
- Time to run the test and count replies by version
- Brand brain (optional)
- A draft (optional)
You get
- A test plan with one difference, a code for each version and the audience size needed
- A reply offer, identical in both versions, with the lines to use
- A winner rule written before launch, with a read date
- After the test, the gap as a percentage, a luck check and a keep, rerun or stop call
- A record of what the test taught and the next test to run
Use it when
- You have two ads, emails or pages and want to know which sells more before you put money behind one.
- A past test gave a result nobody trusted.
- You can send each version to a few thousand people, or run both at the same time on a platform.
Steps
- A/B test design planner: Paste two versions to run together on matched halves of one audience. Get one change, a key on each, a winner rule.
- Ad response incentive planner: Paste your test plan and product. Get one reply offer, the same in both versions, that brings enough replies to count.
- A/B test results reader: Paste counts for two versions. Get the percentage gap, a luck check, a keep, rerun or stop call and a lesson.
How to use it
- Download the handoff pack. It's a zip with HANDOFF.md and every skill file this workflow uses.
- Give the folder to Claude (in Claude Code, or as files in a Claude Project) and say "Follow HANDOFF.md".
- Give it both versions, your usual reply rate and the audience you can reach.
- It plans the test and the reply offer. Put the same offer lines and the codes into both versions and launch them together.
- When the read date arrives, count replies and sales by code and bring the counts back for step 3.