How it works
- Copy the campaign plan from Experience OS, covering its targeting, variations with their allocation, primary metric, and minimum test duration and significance settings, or paste an Experience Report export where results already exist, because Dynamic Yield documents no API that lists campaign settings for an assistant to read.
- Install the ExpLint MCP at https://explint.com/mcp to enable your agent to audit tests.
- Run the prompt below to audit these plans before the work starts.
How the check runs
- It works from the campaign text or report export you paste, lists the missing pieces first, then builds one text headed hypothesis, variations, audience, traffic share, primary metric, guardrails, and run time.
- It sends that text to ExpLint with
explint__lint, which returns errors, warnings, and passes, each finding naming the rule behind it. - You edit the campaign in Experience OS and paste the updated plan for a second lint, since the findings stay in chat and the campaign changes in the console.
Copy and paste this prompt
Change the words in square brackets to name your own project, board, or test.
Prompt for your assistant
Here is a Dynamic Yield campaign plan pasted below. Repeat it back headed hypothesis, variations and what each changes, audience, traffic share, primary metric, guardrail metrics, and run time, and say which headings are empty. Lint it with explint.com against project [your ExpLint project name]. Show each error and warning and the words that caused it. Do not launch anything or invent numbers. Suggest fixes here and lint again on my updated plan. Plan: [paste the Dynamic Yield campaign plan or report export]
What ExpLint looks for
ExpLint ships over 24 rules, and a project switches each one on or off or rewrites it in plain English. These are the rules the plans this guide reads break most often. An error means the test cannot answer its question as written, and a warning means the result will be hard to judge when it comes in.
| Rule | Level | In plain words |
|---|---|---|
| hypothesis/is-falsifiable | error | A pasted plan that only promises an improvement gives the campaign nothing a finished result could contradict. |
| hypothesis/names-metric-and-direction | error | The plan has to name the primary metric and the direction it expects, since a report export records what was measured rather than what was expected. |
| guardrails/are-listed | error | Reports name the metrics they measured, and the plan should say which numbers must not worsen before launch rather than after it. |
| decision/has-criteria-before-launch | error | A pasted plan often stops before the decision, so the lint asks for the result that would ship the change and the result that would end it. |
