Cavity pressure transducers have become one of the most powerful diagnostic and control tools in modern injection molding, providing direct insight into the conditions inside the mold cavity. Their integration into adaptive and self-tuning control systems – ranging from rule-based iterative learning to adaptive model predictive control (MPC) and data-driven machine-learning controllers – has enabled shot-to-shot compensation for material and environmental disturbances. This paper presents recent empirical and methodological contributions, highlighting representative experimental validations and industrial implementations (including ENGEL’s iQ Weight Control). The review emphasizes both process gains (reduced weight variation, improved defect detection, increased process capability) and practical constraints (sensor integration, data handling, control stability), and it presents a focused discussion on hot-runner balancing via cavity pressure measurement and its operationalization in production. The discussion addresses pressure-based V/P switchover detection, the use of the pressure integral as an indicator of part mass, gate freeze-off identification, and the effects of temperature gradients and geometric tolerances on flow balance. Reported cases show up to 85% reduction in shot weight variation, about 50% shorter setup, and 20–30% scrap reduction in multi cavity production. The biggest gains have been seen in single cavity tools and valve gated multi cavity molds; for cold runner molds, comparable benefits depend on balancing capability and targeted sensing.