Feedback Form Response Drafter

WHAT IT DOES

AI-powered feedback form response drafter that creates professional, helpful replies to customer feedback. The script reads a feedback form, survey, or customer feedback from the current page—questions, feedback text, ratings, comments, and user context—and generates a draft response to the feedback. The AI produces a well-crafted response that acknowledges the feedback, addresses any concerns, thanks the user, and outlines next steps if applicable. You can customize the response type (acknowledge/thank_you/address_concern/follow_up), tone (professional/warm/friendly), length, and toggle inclusion of action items and appreciation. The user reviews the output before copying or using it.

WHERE IT RUNS

Works on all feedback form and survey pages (match pattern *://*/*), including customer feedback forms, survey platforms, review pages, customer service portals, and any page containing feedback or survey content.

HOW TO USE

Install the script and navigate to any feedback or survey page. The Feedback Form Response Drafter appears in the panel. Configure your preferred response type, tone, length, and toggle inclusion of action items and appreciation using the settings controls. Click "Draft Response" to analyze the current page. The AI extracts feedback content and generates a professional response. Review the output in the panel. Click "Copy to Clipboard" to copy the response for use in customer support, email, or communication platforms. Adjust the settings and regenerate if you want a different tone or type of response.

REAL MECHANISM: DOM CONTENT EXTRACTION WITH AI FEEDBACK RESPONSE DRAFTING AND REVIEW GATE

This script uses a hybrid extraction approach that prioritizes structured content when available. First, it checks for WebMCP (navigator.modelContext), a W3C proposal that exposes structured tools on the page. If available, it calls getContent() to obtain structured feedback data. If WebMCP is not present—the common case today—it falls back to DOM scraping using targeted selectors for feedback sections (feedback-text, customer-feedback, survey-response, feedback-comment, rating-text, feedback-details, user-feedback, comment-box, review-text, and customer-comment). It also scans for feedback keywords (feedback, rating, comment, suggestion, review, complaint, praise, concern) to capture relevant content. The extracted text is sent to an AI backend via GM_xmlhttpRequest, which processes it with a system prompt that includes the user's response type, tone preference, length, and inclusion preferences. The AI returns a draft response (80-200 words depending on the selected length) that acknowledges feedback, addresses concerns, thanks the user, and outlines next steps. The response is displayed in a bordered container for review before copying. Copy-to-clipboard uses GM_setClipboard. All settings (responseType, tone, length, includeActionItems, includeAppreciation) are persisted via GM_setValue. The script enforces a review-before-use pattern: the user must read and approve the AI output before copying it.

THE PANEL

Drag the panel anywhere on screen by clicking and holding the header. It snaps to screen edges when released. Collapse it to a small bubble by clicking the minimize button, and expand it back by clicking the bubble. Resize the panel from any corner. Press Escape to close the configuration panel. Your position and size preferences are saved automatically per site.

PLEASE NOTE

This script requires the free BotGentz browser extension and an active AI subscription for the drafting service. AI-generated responses should be reviewed for accuracy and appropriateness before sending—the AI may misinterpret feedback or generate a response that doesn't match your company's voice. The script reads the current page content and sends it to the AI backend for processing; no data is stored or logged. Websites change frequently; if the script stops detecting feedback content, check for updates to the extraction selectors.