Multi-Language Email Reply Drafter

WHAT IT DOES

Multi-Language Email Reply Drafter reads the email thread, detects the language of the original message, and generates a reply in that same language (or your specified target language). It preserves your intended message and key points while adapting to appropriate linguistic and cultural nuances. Choose from 14 languages including English, Spanish, French, German, Japanese, Chinese, Arabic, and more. Set formality level (Informal, Neutral, or Formal) and toggle tone preservation. Perfect for international correspondence, multilingual teams, customer support in multiple languages, or any situation where you need to reply in the recipient's language.

WHERE IT RUNS

Any webpage with email threads, message conversations, or support tickets—Gmail, Outlook, Yahoo Mail, LinkedIn messages, Slack threads, Zendesk, Intercom, and more. The script scans the page for conversation context: subject lines, sender information, message bodies, and quoted replies. No site-specific configuration needed; the detection algorithm adapts to the page structure automatically.

HOW TO USE

Install the script and navigate to any email thread. Enter your key reply points in the text area (what you want to say). Click "Analyze Thread"—the tool extracts the conversation context and detects the original message's language. Choose your target language (Auto-detect or manually select one of 14 languages). Select formality level and toggle tone preservation. The draft appears in the panel in the target language. Review it, edit if needed, then click "Insert" to place it directly into your reply field, or "Copy" to paste elsewhere. Settings persist per site and globally—the tool remembers your language, formality, and tone preferences. Keyboard shortcuts: Ctrl+Shift+L to analyze and generate, Ctrl+Shift+R to regenerate, Ctrl+Shift+I to insert.

TECHNICAL MECHANISM

The script extracts email content using a cascading DOM selector strategy: it targets subject lines (h1[data-thread-perm-id], .hP, .subject), sender information (.gD, .go, [email]), and message bodies (.ii.gt, .a3s, .msg-body, [role="article"]). Collected text is concatenated with labels into a structured input. The AI prompt includes the full thread content, the user's reply points, target language setting (auto-detect or specified), formality level (informal/neutral/formal), and tone preservation toggle. For auto-detect, the model identifies the source language from the thread and generates the reply in that language. The prompt also instructs the model to adjust for appropriate linguistic and cultural nuances—including word choice, sentence structure, idiomatic expressions, and cultural references. The response is displayed in a textarea with Insert and Copy buttons. Reply insertion uses native value setting with both "input" and "change" events for React/Vue compatibility. The script prefers WebMCP (navigator.modelContext) when available, falling back to DOM scraping when not.

THE PANEL

The tool runs inside BGPanel, a lightweight UI system built into the BotGentz extension. Drag the panel by its header to reposition it anywhere on screen—it snaps to edges and remembers its position per site. Click the header to collapse the panel into a small bubble; click again to expand. Resize the panel by dragging its bottom-right corner. Press Escape at any time to close the panel. The panel stays out of your way but is always accessible via the extension's toolbar.

PLEASE NOTE

Requires the free BotGentz browser extension and an active monthly subscription—the AI backend uses credits for each generation. One generation per click; regenerate counts as a new generation. The script reads only what is visible on the page—it cannot access iframes or shadow DOM. AI-generated multi-language replies are suggestions—always review and edit before sending. No email content is stored or shared beyond the API request; all processing is ephemeral. Language detection accuracy depends on the quality of the source text—very short or mixed-language messages may be misidentified. Sites change their markup over time; if detection fails, check for updates or use the tool on a page with clearly visible conversation content.