Rough prompt in. Clear prompt out.

It rewrites a rough prompt into a single, clearer one — built to preserve your intent and add nothing you didn't say; always plain text, under 500 characters. Select text in any field and click Refine, press Alt+Shift+R, or use the scratchpad in the popup.

An optimizer. RefineIQ doesn't write prompts from scratch — it takes the rough prompt you already typed and rewrites it into a clearer, better-structured one that preserves your intent. If you want a starting point instead, dictate a quick Voice Draft and refine that.

Generators invent prompts from a topic or form. RefineIQ is a prompt rewriting / improvement tool: you stay the author, it clarifies structure and wording. Template libraries (like AIPRM-style packs) solve a different job — inspiration — not cleaning a messy draft you already wrote.

Not in the default on-device mode. Inference runs in your browser via WebGPU (WebAssembly fallback). There is no RefineIQ server to receive prompts. Optional bring-your-own-key cloud mode sends text only to the provider you chose, with your own key, directly from the browser.

Yes. By default everything runs on your device and nothing you type leaves your machine. There is no RefineIQ server, no account, and no tracking of any kind.

No. On-device mode needs no key and no account — just a one-time model download. A key is only for the optional bring-your-own-key cloud mode, and it stays on your device.

Roughly 380 MB for the default model (a lighter ~130 MB tier is available in Settings), downloaded once and cached. On a machine with WebGPU it loads in a few seconds thereafter.

In on-device mode, yes — fully, after the one-time download. Cloud mode needs a connection, since it calls your own provider.

Yes. Purpose-built support for ChatGPT (chat.openai.com / chatgpt.com): select text in the composer, click Refine or press Alt+Shift+R. See the ChatGPT prompt optimizer page for details.

Yes — on claude.ai and anywhere else you type. Select your draft and refine in place. See the Claude prompt optimizer page.

Yes — Gemini and Google AI Studio, plus any text box. See the Gemini prompt optimizer page.

Any page with a normal text field, textarea, or editable box — with purpose-built support for ChatGPT, Claude, Gemini, AI Studio, and Perplexity (and it works in Grok and other chat UIs the same way). You can turn it off for specific sites under Settings → Sites.

Yes. Paste or select a rough coding ask — debug steps, review criteria, stack constraints — and RefineIQ clarifies structure without inventing APIs or requirements you didn't state.

Yes. It rewrites writing, editing, and research prompts the same way: clearer goal, audience, and output shape, while preserving your intent.

Voice Draft is push-to-talk and always local: speech is transcribed by a small model running entirely on your device. Audio is never stored and never sent anywhere — RefineIQ deliberately avoids the browser's built-in speech recognition because Chrome implements it server-side.

Free, with no paid plans, subscriptions, or ads. If it saves you time, there's an optional support link in the popup — that's the only monetization.

Yes, in two ways. On-device refining is free and uses no AI provider tokens or credits — you're not paying an API to clean up a prompt. And a clearer, tighter prompt gets a usable answer on the first try, so you burn fewer tokens on the back-and-forth of fixing a vague one.

That's the point of on-device mode: your drafts are processed by a model running in your own browser, so sensitive text stays inside your environment and is never sent to RefineIQ — there is no RefineIQ server to receive it, log it, or leak it. Cloud mode is strictly opt-in and, when enabled, sends prompts directly to the provider you chose with your own key.

Chrome and Chromium browsers on desktop — Edge, Brave, Opera, Vivaldi, Arc. Chrome 113 or newer is required (it's also the WebGPU baseline; devices without WebGPU fall back to a slower on-device path). A Firefox build is maintained for portability.