Agent-based modelling in the form of multi-agent models has been increasingly applied to the simulation of spatial phenomena in silico . Validation and calibration are recurrent problems. The complexity of these models with large numbers of parameters can make validation procedures intractable. In this paper, the novel concept of using agent-based technologies to create services that assist in the validation and calibration of multi-agent models is developed. Such agent-based services offer an efficient solution where large numbers of model runs need to be carried out. In this paper, the agent-based services are collaborative sets of agents that perform calibration and sensitivity analysis as a key task in model validation. In a case study, the prototype agent-based validation services are implemented for a multi-agent wayfinding model as a means of proof-of-concept. The case study demonstrates how agent-based services can be deployed for testing the robustness of emergent patterns through sensitivity analyses and used for model calibration.