The SAFECITI project proposes the creation of a simulation system for Police intelligence analysts to predict the behavior of crowds in urban environments under specific threats or stresses (turmoil, violence, panic, catastrophes or terrorism) in order to train and develop better safety plans, and tactic operations. This platform will be designed both as a simulation platform for training purposes and as a predictive tool for operational use. The platform will also include performance measurement tools based on safety goals (people and infrastructure damage) to measure the skills of the analyst.All the simulations will be stored in a database for further analysis, creating a large set of data that can be exploited. The database will work as an historic repository, but more interestingly, as a large set of useful data that will be re-analyzed by artificial intelligence algorithms to create predictive models. The main goal of this predictive model will be the creation of a virtual analyst that is able to recommend actions based on the enriched analysis of hundreds or thousands of simulations.This project aims not only to improve the training methodologies and performance measurement of the analysts, but to create a new profile for new generation analysts that will get trained in a first stage and will operate the system later along their whole operational life, helping to enrich the system with new simulations and validation cases. These new analysts will be able to project new operational plans in advance by simulating “what-if” cases in complex scenarios, and anticipating threats.The Consortium is an outstanding example of multi-sector collaboration between research excellence institutions, large corporation, end user and SMEs from five European Countries. Three SMEs are involved, one large corporation, one University and an end-user (Spanish National Police). All of them play a relevant role in the project. The Coordinator is Next Limit Technologies (SME).