Custom lint rules
Toggle the built-in rules on or off, and add rules you want your agents to follow.
Make your new Growth PM
Press to show the next assistant.
Install the ExpLint MCP and flag inconsistencies, missing metrics, and anti-patterns across your A/B test backlog.
Built by growth engineers from
Try the real-time linter
hypothesis.md2 errors, 4 warnings
Shorten first-run setup to lift activation
Hypothesis
If we cut first-run setup from six steps to two and auto-fill the workspace name, then more companies will run better experiments, because less setup time leaves more room for testing.
Research
Growth teams keep describing the same failures: setup takes too long, and the first experiment never ships. Support keeps hearing it on calls, and trial accounts go quiet right after the first session.
Success metric
New workspaces that launch an experiment within seven days of signup.
Guardrails
Keep an eye on support volume in the first week, and make sure mobile setup doesn’t slip.
Rollout
10% of new workspaces for 7 days, then half, then everyone. Stop if activation falls by more than three points in any cohort.
How it works
Install the connector once, then keep working in whatever assistant you already use.
Install the MCP in Claude, ChatGPT, or Grok Bot
, or add https://explint.com/mcp as a connector in settings. Cursor and Gemini read the same server URL.
Ask your agent to lint your test backlog
Point it at a backlog or a folder of specs. Every finding comes back with the rule it broke and the line it broke on.
Iterate on your A/B test specs
Ask your agent to fix the highlighted issues, and repeat until green. Your specification will now follow A/B test industry best practices.
Tools a growth team needs to scale
Set up custom lint rules per project, team, or feature. Use ExpLint wherever you’re working: MCP, API, or Analytics.
API
Send a spec over REST and get the findings back as JSON, with the rule and the line that broke it.
- One request per spec
- Findings carry rule and line
MCP
Add explint.com/mcp to Claude, ChatGPT, or Cursor, and the assistant calls the linter for you.
- One server URL, no key
- MCP tools in every assistant
Analytics
Quality scores accumulate with every lint, so a weakness that keeps appearing across specifications becomes visible as a pattern the team can fix once.
- Understand recurring quality issues across linted A/B test specifications
- Catch drift between experiment platform outcomes and what was agreed at launch
- Platform-agnostic quality assurance for experimentation programmes
Projects
Give each project its own rules, whether it’s a feature, a team, or a client.
Start free, pay for what you lint
Try it free with up to 50 basic lint requests, then top up for access to advanced linting and custom rules.
Free
$0/ month
- Up to 50 basic lint requests
- Up to 1 project
- MCP/API support
Pay As You Go
| Lint | Per request | What you get |
|---|---|---|
| Basic lint | $0.0083 | Errors, warnings, and a quality score |
| Advanced lint | $0.05 | Full report with line by line breakdown for each error and warning using SOTA models |
- Advanced linting
- Unlimited projects
- MCP/API support
- Custom rules
A lint request is counted only when the lint tool or endpoint is called. Editing rules or creating projects costs nothing.
Questions
What counts as a lint request?
A basic lint is priced at $0.0083 per successful lint and returns the errors, warnings, and overall quality score for an A/B test. A more advanced lint uses smarter models and also returns the parts of the spec that need to be rewritten, and it is priced at $0.05 per successful lint.
Which assistants can install it?
Claude, ChatGPT, Grok Bot, Cursor, and Gemini all work. Claude takes a one-line command, and everywhere else you paste the server URL as a connector or MCP server.
Do I need to learn the API?
There is nothing to learn. The MCP exposes the linter as tools your assistant calls in plain language, and the API is there when you want the same rules inside your own app.
Can I add my own rules?
You can toggle the built-in hypothesis rules on or off, and add rules for the mistakes your team keeps catching by hand.
What does the linter check?
The linter checks your spec against the rules in your project, covering hypothesis, research, design, and metric setup.
Can I try it without an account?
Try the live demo above. To use it from Claude or ChatGPT, create an account to install the MCP.
Don’t let a bad test make it to production
Install the MCP and start flagging ticket slop before it reaches your users
