Aberrant inflammation in the central nervous system (CNS) has been implicated as a major player in the pathogenesis of human neurodegenerative disease. However, the specific contribution of each cell type to the neuroinflammatory axis in vivo remains unclear with species-specific differences in key signaling pathways further complicating the challenge. To assemble a fully human platform to study neuroinflammation, we first developed a novel approach to derive microglia from human pluripotent stem cells (hPSCs) that faithfully recapitulates microglial ontogeny as validated by single cell RNA-sequencing and stage-specific mapping onto datasets of developing mouse microglia. Using these cells, we build the first defined and completely hPSC-derived tri-culture system containing pure populations of hPSC-derived microglia, astrocytes, and neurons to dissect cellular crosstalk along the neuroinflammatory axis in vitro. We next used the tri-culture system to model neuroinflammation in Alzheimer’s Disease using hPSCs harboring the APPSWE+/+ mutation and their isogenic control. Our data reveal that production of complement C3, a protein that is increased under inflammatory conditions and implicated in synaptic loss, is potentiated under tri-culture conditions, and is further enhanced in APPSWE+/+ tri-cultures. Using cell type-specific ablation studies, we report that C3 potentiation is due to the presence of a neuroinflammatory loop in which microglia are the key initiators that activate reciprocal signaling with astrocytes to produce excess C3. Our study defines the major cellular players contributing to increased C3 in AD and presents a broadly applicable platform to study neuroinflammation in human disease. Overall design: Cell heterogeneity was assessed at timepoints during in vitro human primitive hematopoiesis using single-cell RNA-sequencing to identify the early trajectories of differentiating microglial cells.