From: Stefan Gasser Date: Sun, 28 Jun 2026 23:23:52 +0000 (+0200) Subject: Refine positioning copy X-Git-Tag: v0.7.3~1 X-Git-Url: http://git.99rst.org/?a=commitdiff_plain;h=55f9d89d89435df6d67793775bcd087a30de28f9;p=sgasser-llm-shield.git Refine positioning copy --- diff --git a/README.md b/README.md index 511ef39..b3ccd4b 100644 --- a/README.md +++ b/README.md @@ -47,7 +47,7 @@ It works in three places: **ChatGPT, Claude, and Gemini.** Paste customer notes, contracts, support tickets, candidate details, or internal context without sending the raw private values to the chat provider. You see the originals; the AI sees placeholders. -The browser extension is currently in beta. +The browser extension beta is available for ChatGPT, Claude, and Gemini. **[Install browser extension](https://pasteguard.com/browser-extension)** · **[Browser Chat docs](https://pasteguard.com/docs/use-cases/chat)** @@ -73,7 +73,7 @@ Use it when your current options are: - Do not use cloud AI for sensitive work - Redact client or production data manually -- Fall back to a weaker local model because the provider cannot see real context +- Switch to a local model even when a cloud provider would give better results - Build one-off masking code inside every app ## Quick Start diff --git a/docs/concepts/local-first-privacy.mdx b/docs/concepts/local-first-privacy.mdx index 9ac6a1b..39ed176 100644 --- a/docs/concepts/local-first-privacy.mdx +++ b/docs/concepts/local-first-privacy.mdx @@ -47,7 +47,7 @@ Restoration depends on the provider endpoint and response format. OpenAI Chat Co ## Browser Extension -The browser extension is currently in beta. It uses a local PasteGuard server for masking and restoration so browser chat can follow the same privacy model as the proxy. +The browser extension beta uses a local PasteGuard server for masking and restoration so browser chat can follow the same privacy model as the proxy. ## Logs And Dashboard diff --git a/docs/introduction.mdx b/docs/introduction.mdx index bd0c40b..cc10401 100644 --- a/docs/introduction.mdx +++ b/docs/introduction.mdx @@ -30,7 +30,7 @@ It is built for teams that want to use AI with real context but cannot send raw PasteGuard gives teams a local or self-hosted control point before requests reach AI providers. -Use it when the current options are manual redaction, no cloud AI for sensitive work, a weaker local-only model, or custom masking code in every app. +Use it when the current options are manual redaction, no cloud AI for sensitive work, local-only models where a cloud provider would work better, or custom masking code in every app. diff --git a/docs/use-cases/chat.mdx b/docs/use-cases/chat.mdx index 20a5a1b..74e4108 100644 --- a/docs/use-cases/chat.mdx +++ b/docs/use-cases/chat.mdx @@ -9,7 +9,7 @@ Browser Chat protects what people already do: paste real context into ChatGPT, C PasteGuard masks names, emails, account details, customer notes, contracts, support tickets, and other sensitive values before they reach the chat provider. You keep the originals. The AI sees placeholders. -The browser extension is currently in beta. +The browser extension beta is available for ChatGPT, Claude, and Gemini. ## Supported Platforms diff --git a/docs/use-cases/regulated-teams.mdx b/docs/use-cases/regulated-teams.mdx index 7f0d300..091fda2 100644 --- a/docs/use-cases/regulated-teams.mdx +++ b/docs/use-cases/regulated-teams.mdx @@ -14,7 +14,7 @@ Teams usually choose one of these options before adopting a privacy layer: - Avoid cloud AI for sensitive work - Redact client or production data manually -- Use a weaker local model because cloud providers cannot receive raw data +- Switch to a local model even when a cloud provider would give better results - Build one-off masking code inside each app PasteGuard is designed to replace that manual step with a consistent control point.