How it works
- Connect Wingify's MCP server at https://mcp.wingify.ai/mcp to your AI assistant or coding agent, then sign in with the VWO account holding the campaign.
- 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 reads the campaign's hypothesis, variations with what each changes, traffic split, and goals, then builds one text with headings taken from those fields and flags the empty ones before checking.
- 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 VWO and ask for a fresh read and lint, and the report should come back with the errors cleared before the campaign goes live.
Copy and paste this prompt
Change the words in square brackets to name your own project, board, or test.
Prompt for your assistant
Read the VWO campaign [campaign name] with Wingify MCP tools. Build one text from hypothesis, variations and what each changes, traffic split, primary and other goals, and planned run time. Lint it with explint.com against [your ExpLint project name]. Show each error and warning with its VWO setup step. Do not start or edit it yet. Suggest fixes here and re-check after I update VWO.
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/names-metric-and-direction | error | The campaign hypothesis has to name the goal and the direction it expects, since VWO records the goal as a setting and the prose carries the expectation. |
| metrics/has-one-primary-metric | error | VWO lets a campaign carry several goals, and the plan has to say which one decides the outcome when they disagree. |
| power/states-the-minimum-detectable-effect | error | The campaign should name the smallest lift worth acting on, because a goal and a traffic split alone cannot say whether that lift is visible. |
| duration/covers-full-business-cycles | error | The campaign should run across full weeks, since a window that starts on a Tuesday weighs the quieter weekend days differently from a full cycle. |
