Everyone hates waiting for the cable guy? Every time that you need service, you schedule an appointment and get a four-hour time window or the cable company gives you a small time window but invariably is late and makes you wait. Firms serving customers at their homes face the challenge of assigning time windows small enough to respect busy schedules, but large enough to provide adequate service. The problem is that, at the that you make a request, the company does not know everyone who will need to be served on the same day as you. Thus, they need an accurate estimate of when the technician will arrive to your home and need to match a reasonable time window to it. In this talk, we will first discuss a method for estimating arrival times. The proposed approach provides a state-dependent estimate, relying on a state-space aggregation to account for the nearly infinite state space. We then demonstrate a dynamic strategy for setting time windows as a function of arrival time variance and show that they perform significantly better than static policies.