5 items
Personalized AI SDR for Commercial Real Estate (Beta) Kalven is a personalized AI SDR for commercial real estate brokers. The Beta version currently runs inside your existing tech stack, qualifies properties on your behalf, identifies the contacts behind them, and generates a structured Excel workbook with prioritization and outreach recommendations. What Kalven does in the Beta: • Reads property data from the platforms you are already authenticated on (currently CoStar) • Cross-references contact and ownership information from supporting sources (currently TitlePro247) • Sends the structured dataset to the Anthropic Messages API for analysis using your own API key • Generates a downloadable Excel workbook with property scores, contact lists, and draft outreach Bring your own everything: • Your own platform subscriptions (Kalven does not provide platform access) • Your own Anthropic API key (you pay for API usage directly) • Your own browser session and credentials (Kalven does not store platform logins or data) Privacy and data handling: • No Kalven servers or shared infrastructure • Property, contact, and financial data are held only in browser memory during your active session and never written to persistent storage • Your Anthropic API key is stored locally in chrome.storage.local, encrypted at rest by Chrome, and never transmitted anywhere except as an authentication header to api.anthropic.com • No telemetry, usage analytics, or crash reporting What Kalven does NOT do: - Does not bypass authentication on any platform - Does not access data the broker is not already entitled to see - Does not store, sync, or transmit property/contact/financial data to any Kalven-controlled server (Kalven has no servers) - Does not sell, resell, or redistribute platform data - Does not scrape data outside the broker's active browser session debugger permission, specifically: CoStar's search form uses third-party JavaScript widgets that mask input fields and reject standard programmatic input/change DOM events as untrusted. Standard chrome.scripting.executeScript attempts were tested and confirmed insufficient. Kalven uses chrome.debugger only on the active CoStar tab, only after the user clicks "Analyze," only to dispatch trusted keyboard events via Chrome DevTools Protocol (Input.dispatchKeyEvent) to those specific masked fields, and immediately detaches after the input step. It does not read network traffic, intercept responses, debug arbitrary tabs, or operate outside product.costar.com. Data flow: Platform pages (currently CoStar/TP247) → browser memory (transient) → Anthropic Messages API via the broker's own API key → JSON response → Excel file in the broker's local Downloads folder. Nothing else. Privacy policy: https://www.kalven.ai/privacy.html Happy to provide a video walkthrough of the debugger-input step or any other clarification. Beta software: Kalven is in beta. Feedback: joe@kalven.ai
May 23, 2026
rating_count is the Chrome Web Store ratings count, not a written-review count.
Media assets
Screenshots and videos on the listing.
Has promo video
Whether the listing includes at least one video.
Languages
Declared language locales.
Developer website
Listing exposes a developer website URL.
Contact email
Listing exposes a contact email.
Keyword in name
Case-insensitive substring match in the name.
Keyword in description
Case-insensitive substring match in the description.
Keyword occurrences in description
Count of case-insensitive occurrences in the description.
Category user-count percentile
Share of same-category extensions with fewer users (null if unknown).
These are transparent listing completeness / keyword signals, not a prediction of Chrome Web Store search ranking.