Catch vague Trello cards before they reach Ready

Cards on an experiment board carry checklists and labels, and a check on each one shows which cards are ready to leave the Ideas list.

How it works

  1. Connect Trello's MCP server at https://mcp.trello.com/v1 to your AI assistant or coding agent, then sign in and approve access to your experiment board.
  2. Install the ExpLint MCP at https://explint.com/mcp to enable your agent to audit tests.
  3. Run the prompt below to audit these plans before the work starts.

How the check runs

  1. It opens each card in your Ideas list for the name, description, checklists, and labels, since a card often spreads its plan across all four.
  2. It sends that text to ExpLint with explint__lint, which returns errors, warnings, and passes, each finding naming the rule behind it.
  3. On approval it comments the findings and the draft on the card, and it can move the card to your Ready list once a fresh check comes back clean.

Copy and paste this prompt

Change the words in square brackets to name your own project, board, or test.

Prompt for your assistant
Use Trello MCP tools to read every card in [Ideas] on board [board name]. Lint each card's title, description, and checklist with explint.com against project [your ExpLint project name]. Show card names with errors and warnings, grouped by most common gaps. Do not change cards yet. On my approval, comment findings and a suggested rewrite on the card, lint the rewrite, and report whether errors cleared.

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.

RuleLevelIn plain words
hypothesis/is-falsifiableerrorA card that describes a change and a hope gives the board nothing a finished test could contradict.
hypothesis/is-based-on-evidenceerrorThe card should point at a metric reading, a support thread, or an earlier test, because an idea with no source is the one the lint marks.
metrics/has-one-primary-metricerrorOne number has to decide the result, and a card that names three wins cannot be judged by any of them.
duration/covers-full-business-cycleserrorThe card should say how many full weeks the test runs, since a label and a due date do not tell the next person what the window covers.

Read more

Portrait of Kameron Tanseli

Kameron Tanseli

Founder, ExpLint

Kameron Tanseli is the founder of ExpLint and a growth engineer who has run more than 1,500 experiments across a nine-year career. As the founding growth hire at Fyxer he launched 540 experiments in a year while the company grew from $1M to $35M in annual revenue, and he now runs growth engineering at FLORA, where a one-person team ships six to eight experiments a week.

Don’t let a bad test make it to production

Install the MCP and start flagging ticket slop before it reaches your users