How it works
- Connect Adobe Target to your AI assistant or coding agent through your organisation's MCP setup, and confirm with your admin which workspaces you can 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 reads the activity's goal, hypothesis, audiences, experiences with each change, traffic split, and reporting metrics, then writes one text with headings that match the Target screens your approver already knows.
- It sends that text to ExpLint with
explint__lint, which returns errors, warnings, and passes, each finding naming the rule behind it. - You or your approver update the activity and ask for a fresh read, which gives the approval step a report rather than a second opinion.
Copy and paste this prompt
Change the words in square brackets to name your own project, board, or test.
Prompt for your assistant
Use Adobe Target MCP or API tools to read the draft activity [activity name]. Build one text from its goal, hypothesis if written, audiences, experiences and each change, traffic split, primary and guardrail metrics, and run time. State missing fields instead of filling them in. Lint the text with explint.com against [your ExpLint project name]. Show each error and warning with its Target field. Do not activate or edit the activity. Suggest fixes here, and re-check after updates.
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 activity has to say which metric should move and in which direction, since the goal setting alone records what is measured rather than what is expected. |
| guardrails/have-launch-thresholds | error | Each guardrail needs a number the approver can compare against, because a report to watch after launch is not a limit set before it. |
| audience/has-exclusion-criteria | warning | An Adobe Target audience is a targeting rule rather than an exclusion list, so the plan should name the staff, bots, and test accounts it keeps out. |
| decision/has-criteria-before-launch | error | The approval step is the natural place to record what result ships the experience and what result stops it, and the plan should carry that before activation. |
