MarketingSandbox · bring your own key

Test “Ab Test Analyzer” with your own key

Paste an Anthropic, OpenAI, or OpenRouter key. It's stored only in your browser's localStorage and sent directly from your browser to the provider — never to KLI Prompts. We have no backend that can see it.

How this works (honestly)

Your key lives in localStorage on this device only.
The HTTP request to the LLM goes from your browser straight to api.anthropic.com / api.openai.com / openrouter.ai.
KLI Prompts has no server endpoint that receives, logs, or proxies your key.
Clear it any time — there's a button below.

Step 1 · Provider

Recommended for this prompt: any · temperature 0.4

Step 2 · Your API key

Anthropic API key

Saved to localStorage on this device. Never sent to KLI servers.

Model

Temperature

Step 3 · Fill the variables

Metric Name*

Test Duration Days*

Confidence Target*

Control Visitors*

Control Conversions*

Control Rate*

Variant Visitors*

Variant Conversions*

Variant Rate*

Relative Uplift*

Final prompt (sent to anthropic)

Interpret the following A/B test results and return a JSON object with the exact shape specified.

## Test Details
- Metric: {{metric_name}}
- Test duration: {{test_duration_days}} days
- Desired confidence level: {{confidence_target}}%

## Control Group
- Visitors: {{control_visitors}}
- Conversions: {{control_conversions}}
- Conversion rate: {{control_rate}}%

## Variant Group
- Visitors: {{variant_visitors}}
- Conversions: {{variant_conversions}}
- Conversion rate: {{variant_rate}}%

## Pre-calculated Metrics
- Relative uplift: {{relative_uplift}}%

## Instructions
Use approximate z-test reasoning to estimate confidence. Based on the data, provide:
1. A recommendation: "ship" if the variant wins at the desired confidence level, "dont-ship" if it clearly loses, or "run-longer" if there's not enough data.
2. An estimated confidence percentage (0-100) using z-test approximation.
3. Plain-English reasoning (2-4 sentences).
4. 2-3 practical caveats.

Return ONLY valid JSON in this exact shape (no markdown, no code blocks):
{
  "result": {
    "recommendation": "ship" | "dont-ship" | "run-longer",
    "confidence": <number 0-100>,
    "controlRate": <decimal e.g. 0.032>,
    "variantRate": <decimal e.g. 0.041>,
    "relativeUplift": <percentage number e.g. 28.1>,
    "reasoning": "<plain English explanation>",
    "caveats": ["<caveat 1>", "<caveat 2>", "<caveat 3>"]
  }
}

Output — will stream here

Nothing yet. Fill in variables and click Run.

Prompt slug: ab-test-analyzer

Prefer copy-paste? Back to the prompt page →