The ability to accurately classify influenza viruses is critical to understanding patterns of infection, vaccine efficacy, and to the process of developing new vaccines. Unfortunately, this task is hampered both by the virus’ ability to undergo antigenic drift and shift (rendering it a “previously unknown” strain), and by technological limitations. In an effort to overcome these challenges, we have developed a label-free human monoclonal antibody array for flu serology, using a pattern recognition approach to assign virus serotype. The array is built on the Arrayed Imaging Reflectometry (AIR) platform. AIR relies on the creation of a near-perfect antireflective condition on the surface of a silicon chip. When this antireflective condition is perturbed because of binding to an antibody spot (or other immobilized probe molecule), binding may be sensitively and quantitatively detected as an increase in reflected light. We describe fabrication and characterization of the array, and preliminary testing with isolated influenza hemagglutinin. We anticipate that this approach may be extended to other viruses by expansion of the array.