Abstract Study question Can we improve embryo selection and ploidy prediction using novel morphokinetic parameters in blastocyst development, and obtain results comparable to artificial intelligence? Summary answer Time and pattern of novel parameter st2 are related to ploidy. Including them in embryo evaluation improves ploidy prediction, reaching predictive values comparable to AI. What is known already Time-lapse has allowed us to detect more morphokinetic parameters and improve embryo grading systems. However, ploidy prediction still relies on invasive techniques to obtain a reliable result. Artificial intelligence is promising and can already predict blastulation or implantation with good results, but not ploidy yet. Moreover, AI presents some other limitations now, including the black box behind its decisions, which doesn’t allow clinicians to know what parameters are being considered the most. Improving the manual evaluation tools used by embryologists can help improve clinical outcomes until AI is fully introduced in IVF. Study design, size, duration A single center retrospective study was performed. Data included a total of 608 blastocyst from 106 treatments between January 2018 and July 2022. Participants/materials, setting, methods 160 treatments of patients for preimplantation genetic testing cycles were studied. Embryos were cultured in time-lapse incubators and were studied for both morphologic and kinetic parameters. 608 of the embryos developed to good quality blastocyst and were able to be biopsied, and therefore analyzed by PGT for aneuploidies on Day5 o Day6. Annotation of several morphokinetic characteristics was performed on all analyzed embryos. The study was blinded for ploidy and all clinical outcomes. Main results and the role of chance Improved embryo grading systems used by embryologist can reach high predictive values comparable to artificial intelligence. We present a new parameter, “st2, start of t2”, which refers to the first cytoplasmic movements detected at the beginning of the first cell cleavage, as highly implicated in ploidy status. Earlier st2 is associated to better euploidy rates (p < 0.001). Not only the time, but also the phenotype of the movements appears as related to ploidy. Embryos showing none or un-patterned random cytoplasmic movements show a marked tendency towards aneuploidy. Contrary, circular waves prior to cell division are highly associated with euploidy (90% of the cases) (p < 0.0001). The implication of the described parameters was also confirmed by logistic regression, with a receiver operating curve (ROC) value of 0.69 for ploidy prediction (95% confidence interval (CI), 0.62 to 0.76). We processed raw time-lapse images with an automatic annotation software using artificial intelligence and obtained a ploidy predictive value of 0.64. This means that using the optimal parameters in manual embryo evaluation, we are able to improve our grading systems and reach ploidy predictive values comparable than with AI. Limitations, reasons for caution This is a retrospective study. The ploidy predictive potential is now being tested on a prospective study. Wider implications of the findings Optimizing the indicators to select the most suitable blastocyst, like including st2, can help reducing the time until the pregnancy of an euploid baby, avoiding invasive and expensive methods. Moreover, by combining AI with the novel parameter st2 we could improve the potential of the ploidy predictions. Trial registration number not applicable