AI Blocks › Plan what ads to test
Ad test sprint runner
Give it your brand file and results. It plans each test round, reads it when it ends and plans the next.
Ad test sprint runner is a free AI agent for the job "Plan what ads to test". Give the instructions to an AI assistant that supports the required files and tools, then review its output.
Free · No account · Made by AI Blocks · Level: advanced · Thinking: high
What it does
One ad test teaches little. A run of tests teaches a lot, if each round builds on the last. Most people plan a test, read it in a hurry, and start again from scratch, or repeat the same idea in a new colour. This agent runs the whole run. It sets a test budget from your target, finds ideas you have not tried, and lays out the round. When the round ends, it checks the data is enough to read, then reads it. A winning set is left alone and built on. A round that was too small is repeated. A round that lost is checked for sameness: if every ad was the same idea, it finds new ideas; if the ideas differed and still lost, it records the lesson. After three rounds with no winner, it checks whether the problem is the page, not the ads. It never launches…
You give it
- Your brand file with products, claims, proof and buyers
- Your target cost per sale or ROAS
- Past ad results for the last 30 to 90 days
- What you can spend on the whole sprint and per day, and the platform
- Each round's results by ad, when the round ends
- Your question (optional)
- Reference ads (optional)
- Customer words (optional)
You get
- A test budget, a spend limit per ad and a read date for the round
- Five untried ideas, each with designer-ready versions
- A campaign layout with one idea per ad set
- A keep, leave or replace call for each set after each round, and what it means
- A running list of lessons, with dates
- A call on whether the problem is the ads or the page after three rounds
Use it when
- You want to find a winning ad and expect it to take more than one round.
- Your last test did not win and you do not know what to try next.
- You have run tests before but never kept what they taught.
How to use it
- Start a chat with the agent. In Claude Code, add it as a skill or save it in .claude/agents, then ask it to start a sprint.
- Give it your brand file, target, past results and budget. It hands back the round plan.
- Launch the round yourself, or say yes to each step if it is connected.
- On the read date, give it the round's results. It reads them and plans the next round.
- Keep going until a set wins or the cap of three rounds is reached.