Patient diversity and unknown disease cause are major challenges for drug development and clinical trial design for amyotrophic lateral sclerosis (ALS). Transgenic animal models do not adequately reflect the heterogeneity of ALS. Direct reprogramming of patient fibroblasts to neuronal progenitor cells and subsequent differentiation into patient astrocytes allows rapid generation of disease relevant cell types. Thus, this methodology can facilitate compound testing in a diverse genetic background resulting in a more representative population for therapeutic evaluation. Here, we used established co‐culture assays with motor neurons and reprogrammed patient skin‐derived astrocytes (iAs) to evaluate the effects of (SP‐4‐2)‐2,2’‐(1,2‐dimethyl‐1,2‐ethanediylidene)bisN‐methylhydrazinecarbothioamidato‐κN2,κS(2‐)‐copper (CuATSM), currently in clinical trial for ALS in Australia. Pretreatment of iAs with CuATSM had a differential effect on neuronal survival following co‐culture with healthy motor neurons. Using this assay, we identified responding and non‐responding cell lines for both sporadic and familial ALS (mutant SOD1 and C9ORF72). Importantly, elevated mitochondrial respiration was the common denominator in all CuATSM‐responders, a metabolic phenotype not observed in non‐responders. Pre‐treatment of iAs with CuATSM restored mitochondrial activity to levels comparable to healthy controls. Hence, this metabolic parameter might allow selection of patient subpopulations best suited for CuATSM treatment. Moreover, CuATSM might have additional therapeutic value for mitochondrial disorders. Enhanced understanding of patient‐specific cellular and molecular profiles could help improve clinical trial design in the future. Main Points The clinical stage drug CuATSM normalizes aberrant metabolic phenotypes of ALS astrocytes and restores support towards neurons. Patient samples could be stratified based on this phenotype, indicating that the model system might support clinical trial result interpretation or design.