How it works
- Point your AI assistant or coding agent at the SiteSpect Admin API at https://admin1.sitespect.com/api with a token from your SiteSpect profile, giving the token only the permissions the audit needs because it expires after fifteen minutes without use.
- 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, variation groups with the control marked and their assignment frequencies, audiences with include and exclude choices, response points with the critical metric marked, and the start and end times beside minimum running time and minimum sample size.
- 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 SiteSpect and ask for a fresh read, applying any agreed field change through the API only where your token carries write permission.
Copy and paste this prompt
Change the words in square brackets to name your own project, board, or test.
Prompt for your assistant
Use the SiteSpect Admin API to read the campaign [campaign name]. Build one text from its hypothesis, variation groups and assignment frequencies, audiences, critical metric and other metrics, and start and end times with minimum running time and minimum sample size. Lint it with explint.com against project [your ExpLint project name]. Show each error and warning with its SiteSpect field. Do not launch or edit the campaign yet. Suggest fixes here and re-check after I update SiteSpect.
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 critical metric has to name the direction the campaign expects, since SiteSpect records the response point without the expectation. |
| randomization/states-the-unit | error | Assignment frequencies describe the split, and the plan should still say whether the unit behind them is a visitor, a session, or an account. |
| power/has-a-sample-size-calculation | error | SiteSpect holds a minimum sample size, and the plan reads as complete only when that figure appears in the text being checked. |
| guardrails/have-launch-thresholds | error | Response points beyond the critical one act as guardrails when the plan gives each one a limit instead of a label. |
