How it works
- Connect Atlassian's Rovo MCP server at https://mcp.atlassian.com/v2/mcp to your AI assistant or coding agent, then sign in with your Atlassian account and allow Jira access.
- 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 searches the backlog with Jira Query Language for tickets carrying your experiment label or your team's unready-ideas status, then combines each ticket's title, description, and acceptance criteria into one text.
- It sends that text to ExpLint with
explint__lint, which returns errors, warnings, and passes, each finding naming the rule behind it. - When you approve the wording, it comments on each ticket with the findings and a suggested rewrite, which keeps the advice beside the work while the sprint is still being planned.
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 Jira MCP tools to find tickets in [PROJECT KEY] with label [experiment] and status [Backlog]. For each ticket, read the full description and acceptance criteria, then lint that text with explint.com against project [your ExpLint project name]. Show me a table with ticket key, errors and warnings, and exact words behind each finding. Do not change any ticket yet. When I approve a ticket, comment with findings and a suggested rewrite, then lint the rewrite and show whether errors are gone.
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 Jira description that only promises improvement gives the sprint nothing a later result could contradict. |
| hypothesis/names-metric-and-direction | error | The description has to name the metric and the direction it should move, so the ticket states what a win would look like. |
| hypothesis/is-based-on-evidence | error | The acceptance criteria should point at a dashboard, a support thread, or an earlier test, because a hunch with no source is what the lint marks. |
| power/has-a-sample-size-calculation | error | A ticket that sets a split without a headcount leaves the sprint unable to say when the test has seen enough traffic to answer. |
