The formulation and calibration of constitutive models remain a difficult task for materials that exhibit complex nonlinear elastic or inelastic behavior. Therefore, new approaches, generally referred to as data-based or data-driven methods, have become increasingly popular in the computational mechanics community in recent years. However, these approaches require a large amount of data, usually stresses and strains for problems in solid mechanics. In this contribution, we present a consistent two-step approach for the automated calibration of hyperelastic constitutive models which only requires experimentally measurable data. In the first step of our approach, data-driven identification (DDI) is applied to determine tuples consisting of stress and strain states [1]. This method enables to identify these data by only prescribing the applied boundary conditions and the displacement field which can be determined from full-field measurement methods such as digital image correlation (DIC). In the second step of the proposed framework, the data are used to calibrate a physics-augmented neural network (PANN) [2]. This model fulfills all common conditions of hyperelasticity by construction and is very flexible at the same time. The implementation of the PANN model into a finite element (FE) code is straightforward. We demonstrate the applicability of our approach by several descriptive examples. Therefore, two-dimensional synthetic data are exemplarily generated by using a reference constitutive model. The calibrated PANN is then applied in three-dimensional FE simulations, where the solution is compared to the reference model. [1] Leygue, A., Coret, M., Réthoré, J., Stainier, L. and Verron, E., Data-based derivation of material response, Computer Methods in Applied Mechanics and Engineering 331 (2018). [2] Linden, L., Klein, D. K., Kalina, K. A., Brummund, J., Weeger, O. and Kästner, M., Neural networks meet hyperelasticity: A guide to enforcing physics, Journal of the Mechanics and Physics of Solids 179 (2023).