Despite its doubtless success, Constraint Programming (CP) has to face two main challenges to develop its success: solving harder and harder problems, and being accessible to users with little to no CP expertise. To address these challenges, we are exploring the use of Ant Colony Optimization (ACO) to solve problems expressed in a regular CP Solver: ILOG Solver. Basically, ants iteratively build partial solutions, trying to assign as many variables as possible, until a complete solution is found. Pheromone trails are used to guide the construction process with respect to past experiments in an adaptive way. So far the approach has been tested successfully on the car sequencing problem.