Kaizen R/W

Your manuscript stays yours.

Kaizen R/W keeps your manuscript in your browser. We don't keep a server-side copy of your draft, your marks, or your local dictionary. When you ask for a Read or a Write, that passage goes through our proxy to the provider you picked, and the response comes back. Hosted plans run on paid commercial API tiers that don't train on inputs.

Passage goes out. Response comes back. Nothing sticks to the proxy.

  • Draft text, marks, dictionary entries, scan state, and local settings stay in your browser unless you ask for a Read or a Write.
  • If you request access or use account features, KRW may store your email address and account identifiers needed to operate that flow.
  • Your manuscript is never used to train a model. When you request a reading, use Ask-AI, or apply a rewrite, the relevant passage and context pass through KRW's proxy to the hosted provider processing your request, then return a response. Nothing is stored, copied, or reused afterward. BYOK users route directly to their chosen provider with their own key.
  • Hosted free and Pro run on KRW's provider accounts. Bring-your-own-key works on every tier and keeps billing on your side.
  • This site uses Cloudflare Web Analytics, which is cookieless. Cloudflare receives the visited URL, the referrer, browser type, and the IP address that delivered the request, and uses that data to count visits and screen out bot traffic. No cross-site tracking, no profile building.
Back to home

How the request travels.

01

Your browser

Your draft and revision memory live here first. Nothing leaves until you ask for a Read or a Write.

02

KRW proxy

KRW passes the request to the model provider and hands the response back. The proxy carries the passage through; it stores nothing.

03

Model provider

Hosted routes run on paid APIs that don't train on inputs by default. Google's paid Gemini API and Anthropic's commercial API both exclude API traffic from training. Their current docs are the source of truth, linked below.

The provider's current documentation is the source of truth.

Policies and models change. If the work is sensitive, read the provider docs before you send it through hosted AI.

  • Hosted free uses Google Gemini on Google's paid API. Model docs | API terms
  • Pro uses Claude via Anthropic's commercial API. Model docs | Privacy docs
  • Bring your own key works on every tier. Your provider bills you directly. Your key stays in your browser and doesn't burn hosted usage. What the provider does with the text is governed by the account and terms on your key.

No manuscript vault.
The data path is short enough to explain.

Your editing stays local-first. If you'd rather pay your provider directly, BYOK works on every tier.