Building a ‘Research Frontier Radar’

For most of my career, staying current meant scanning a fixed set of journals and a few mailing lists. The pipeline I now run replaces that with a generative collector: it pulls from a wide net, clusters what it finds, and leaves me a short daily brief.

The interesting communication-studies question is not “does it save time” (it does) but “what does delegating surveillance to a model do to the scholar’s sense of the field?” When the radar chooses what counts as the frontier, the frontier is partly authored by the tool.

I am treating the method itself as a research object, not just a convenience. These notes will track what the radar shows me and, more importantly, what it quietly hides.