SummaryResponse-surface modelling and sequential optimization have been used for optimization and characterization of the separation of the enantiomers of citalopram, desmethylcitalopram, and didesmethylcitalopram on an acetylated J~-cyclodextrin column. In the model chosen the separation conditions mobile phase methanol content, buffer concentration, column temperature, and pH were varied to investigate their influence on the chromatography.It was found that what is good for selectivity within an enantiomer pair is bad for selectivity between enantiomer pairs. Because within-pair and belvveen-pair selectivity does not reach its optimum at the same conditions, a middle course approach has to be followed.Use of an experimental design for this investigation enabled understanding of the mechanisms of within-and bel,,veen-pair separation for citalopram, desmethylcitalopram, and didesmethylcitalopram. Sequential optimization can be a quicker means of optimizing a chromatographic separation; response-surface modelling, in addition to enabling optimization of the chromatographic process, also serves as a tool for learning more about the separation mechanism.