> ## Documentation Index
> Fetch the complete documentation index at: https://simpai.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Get started with S.I.M.P. in under a minute

> Learn how to paste your first AI prompt into S.I.M.P., choose a feedback mode, run the analysis, and copy your cleaned prompt in five steps.

S.I.M.P. requires no account and no setup. You paste a prompt, pick a mode, and get back a scored analysis and a rewritten prompt you can take straight to any AI model. Here's how to do it.

<Steps>
  <Step title="Open S.I.M.P.">
    Go to [simpai.netlify.app](https://simpai.netlify.app). No account, login, or installation required — the app runs entirely in your browser.
  </Step>

  <Step title="Paste your raw prompt">
    Click the input field and paste the prompt you want to analyze. This should be the prompt exactly as you'd send it to an AI model — unpolished, unedited.
  </Step>

  <Step title="Choose your mode">
    Select **Be Nice** for constructive, senior-engineer-style feedback, or **Roast Me** if you want the same analysis delivered with considerably less diplomacy. Both modes produce the same structured output; only the tone differs.
  </Step>

  <Step title="Run the analysis">
    Click **Run S.I.M.P.** (or **Roast This Prompt** in Roast Me mode). S.I.M.P. sends your prompt to the backend, which analyzes it and returns your results.
  </Step>

  <Step title="Review your risk score and issues">
    Your result includes a hallucination risk score from 1 to 10, a risk label (Low, Moderate, High, or Critical), and a list of specific issues detected in your prompt. Read through the issues to understand what made your original prompt risky.
  </Step>

  <Step title="Copy your sanitized prompt and take it to an AI model">
    Review the sanitized prompt and the change log explaining what was fixed. When you're ready, use the one-click handoff to open the sanitized prompt directly in ChatGPT, Claude, or Gemini — or copy it manually.
  </Step>
</Steps>

## Example

**Original prompt (before S.I.M.P.)**

```text theme={null}
Write me something about climate change for my presentation.
```

**S.I.M.P. result**

| Field | Value |
| - | - |
| Risk score | 8 / 10 |
| Risk label | High |
| Issues | No audience specified; no format or length defined; "something" is too vague; no angle or argument provided |

**Sanitized prompt**

```text theme={null}
Write a 200-word overview of climate change for a general business audience with no scientific background. Focus on economic risks over the next 20 years. Use plain language and avoid jargon. Format as three short paragraphs.
```

The sanitized version specifies audience, length, focus, tone, and structure — exactly the context a model needs to give you a useful answer instead of a generic one.

<Tip>
  Try running the sanitized prompt through S.I.M.P. again using the **Run Again** button — iterating a few times can dramatically reduce your risk score.
</Tip>

<Note>
  S.I.M.P. cleans prompts — it doesn't answer them. Always take your sanitized prompt to an AI model.
</Note>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.