Ghostly Labs has launched dedicated mobile apps for agents and clients, integrating live MLS search, lead tracking, and their Sarah AI assistant, in a move that coincides with stricter MLS guidelines on AI data use.
Ghostly Labs has widened access to its Phantom Realty Engine by releasing separate mobile apps for agents and clients, bringing live MLS search, lead tracking, comparative market analysis and its Sarah AI assistant to smartphones. The company said the apps went live on 12 August, roughly a month after it first presented Phantom Realty Engine as a single system combining a brokerage website, CRM and AI layer.
The client-facing app gives buyers an agent-branded place to browse live listings, save homes with a partner, request viewings and ask Sarah questions about properties or neighbourhoods. It also lets users request a valuation, which is routed back to the agent as a possible seller lead. The companion agent app moves core CRM and MLS functions into mobile, including listing search and sharing, saved searches, client activity monitoring and CMAs built from comparable sales and market data. Ghostly Labs says the platform runs on WordPress and is designed to keep site and data control with the customer.
The launch lands at a time when MLS organisations are drawing sharper lines around how listing data may be used by AI systems. Under the National Association of Realtors’ IDX policy, participating brokers can display approved listings on websites and mobile apps, but the data is meant for IDX display purposes, with other uses falling under separate MLS permissions and local licensing terms. According to coverage cited by NAR, Milwaukee’s Metro MLS recently went further by requiring express written permission before MLS data can be used for AI training, machine learning, derivative datasets or some predictive and generative processing. Other markets are taking different approaches: Doorify MLS in North Carolina has focused its updated agreement on defining prohibited uses, particularly around consumer data and privacy.
Ghostly Labs has also highlighted early results from an earlier Sarah deployment. When Phantom Realty Engine was introduced in July, the company said the system processed more than 15,000 cold leads, moved 49.5% into an “engaged” category and identified more than 1,400 active buyers, while average time on site rose 6.4 times. Those figures are company-reported and use Ghostly Labs’ own definitions rather than closed transactions, so they should be treated as marketing metrics rather than independently verified sales outcomes. For brokers, the practical question is not simply whether an AI product exists, but whether their MLS permits the underlying data use, how AI responses are supervised and how brokerage and client data is handled.
Disclaimer: This content is intended for informational purposes only. Readers are advised to exercise their own judgement, conduct due diligence, or consult a qualified expert before acting on any information provided.
