Online real estate platforms make property listings widely accessible, yet buyers’ effective search opportunities remain shaped by agents’ informal collaboration networks. Using detailed records of online browsing, offline property showings, and transactions in the Beijing housing market, we recover agents’ collaboration networks from their historical interactions with an unsupervised machine learning method. We find that after contacting an agent, buyers shift their online search toward locations with greater coverage by their agent’s network, and network-linked properties are more likely to receive offline visits, even conditional on prior awareness and local market characteristics. We estimate a structural model of buyer awareness, offline search, and purchase that distinguishes two channels through which agent networks operate: shaping which listings buyers become aware of and steering which known listings they visit. Counterfactuals show that the two channels work in opposite directions: network-based information expands the set of listings buyers know and improves their match quality, while steering diverts their limited visits toward partners’ listings and offsets much of this gain. Broadening collaboration breaks down the silos that agent cliques impose on buyers’ search, substantially improving match quality with only a modest increase in search effort.

Star employees are among a firm’s scarcest resources. Understanding how they create value is central to determining where firms should deploy them. Research on star spillovers has emphasized supply-side channels such as knowledge transfer, peer learning, and collaboration, under which a star’s value depends on interactions with coworkers. We study a different mechanism arising where demand attaches to individual employees rather than to the firm alone. Using intra-firm reassignment of agents across the shops of a large real estate brokerage, we find that shop performance rises immediately and persistently when a star arrives and reverses when she departs. Star arrival sharply expands the receiving shop’s customer pool. Yet the star does not increase her own service volume; instead, coworkers absorb the additional demand, lifting their output by 11.8 percent. Tracing customer inflows across shops, we find the decline at the star’s origin shop accounts for two-fifths of the receiving shop’s gain, with no offsetting decline elsewhere in the firm. Most of the inflow is net new demand the firm would not otherwise have captured. But shop capacity is bounded: as coworkers take on more buyers, conversion does not improve and buyers search longer, with the strain sharpest where the shop is already congested. The same star therefore creates more value in shops with room to serve additional customers and the ability to convert them. These findings reframe star deployment from fostering post-arrival coworker interaction to matching scarce demand-drawing talent to the units best positioned to capitalize on the demand it attracts.