Job Posting Bias Language Checker

WHAT IT DOES

AI-powered job posting bias language checker that identifies potentially biased language in job postings and suggests inclusive alternatives. The script reads a job posting from the current page—job title, description, requirements, qualifications, and language—and analyzes it for biased phrasing. The AI identifies gendered language, age-related terms, ableist language, and other potentially exclusionary phrasing, providing suggestions for more inclusive alternatives. You can customize the analysis focus (all/gender/age/ability), report format (summary/detailed), and toggle inclusion of suggestions, severity indicators, and category breakdowns. The user reviews the output before copying or using it.

WHERE IT RUNS

Works on all job posting pages (match pattern *://*/*), including job boards, company career pages, recruitment platforms, and any page containing job posting content.

HOW TO USE

Install the script and navigate to any job posting page. The Job Posting Bias Language Checker appears in the panel. Configure your preferred analysis focus, report format, and toggle inclusion of suggestions, severity indicators, and category breakdowns using the settings controls. Click "Check Language" to analyze the current page. The AI extracts job posting content and generates a bias analysis. Review the output in the panel. Click "Copy to Clipboard" to copy the analysis for review or revision. Adjust the settings and regenerate if you want a different focus or level of detail.

REAL MECHANISM: DOM CONTENT EXTRACTION WITH AI BIAS LANGUAGE ANALYSIS 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 job data. If WebMCP is not present—the common case today—it falls back to DOM scraping using targeted selectors for job posting sections (job-title, job-description, job-requirements, job-qualifications, posting-content, job-ad, job-listing, description-text, and requirements-list). It also scans for job keywords (job, position, role, hire, looking for, candidate, qualifications, requirements, experience, skills) in paragraphs and headings. The extracted text is sent to an AI backend via GM_xmlhttpRequest, which processes it with a system prompt that includes the user's analysis focus, report format, and inclusion preferences. The AI returns a bias analysis (up to 250 words) that identifies biased language and suggests inclusive alternatives. The response is displayed in a bordered container for review before copying. Copy-to-clipboard uses GM_setClipboard. All settings (analysisFocus, reportFormat, includeSuggestions, includeSeverity, includeCategoryBreakdown) 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 analysis service. AI-generated analyses should be reviewed for accuracy before use—the AI may misinterpret language or miss subtle biases. 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 job posting content, check for updates to the extraction selectors.