Beginning in January 2013, the American Community Survey (ACS) added an Internet response option as a fourth mode of response to their existing mixed-mode survey. Motivated by the need to provide cheaper, faster, and better statistical information, the Census Bureau has outlined a vision that includes the future use of adaptive survey design methods. Potential benefits include a reduction in nonresponse follow up lag time, a convenient or preferred mode of response, and cost savings by maximizing response in the cheaper modes. As a first step in addressing this vision, we explore the use of adaptive survey design methods in the ACS by linking administrative data to the April 2011 ACS Internet Test sample to develop a model-based assignment of mode switch strategies, focusing only on switching Internet nonrespondents to mail. We describe the combined use of survival analysis and optimization methods to assign cases to a given mode switch strategy. We simulate the adaptive survey design process and review the cost-benefit trade-offs of using an adaptive versus a non-adaptive approach. In addition, we attempt to validate our approach using the November 2011 Internet Test sample.