In the late 1990s, Switzerland introduced an ambitious active labour market policy (ALMP) encompassing several programmes. We evaluate their effects on the individual employment probability using unusually informative data from administrative records. Using a matching estimator for multiple programmes, we find positive effects for one particular programme unique to the Swiss ALMP. It consists of a wage subsidy for temporary jobs in the regular labour market that would otherwise not be taken up by the unemployed. We also find negative effects for traditional employment programmes operated in sheltered labour markets. For training courses, the results are mixed.