Our industry has been advancing drilling automation concepts to increase safety, reduce drilling risk, and improve the overall repeatability of the drilling process. At the same time, increased drilling costs, available expertise shortage, and safety-related issues with personnel at the wellsite, have prompted the need to provide interpretation and advice remotely.Remote centers enable subject matter experts (SMEs) to work on multiple, geographically dispersed wellsite operations concurrently without having to be on location. These centers facilitate the ability of multiple experts to assemble quickly and collaborate to solve complex challenges without adding the HS&E risk of additional personnel at the wellsite. However, the increased volume of information available from technologies like wired-pipe, combined with the shortage of experienced SMEs to quickly interpret datasets, create new challenges.Digital oilfield applications have challenged operators and service providers to leverage remote capabilities to aggregate huge data volumes and provide expert knowledge for multiple operations. Focusing attention of personnel on the most important information to make accurate and timely decisions requires new techniques. New systems require automation so that risk recognition and advice can be automatically delivered to the right experts to streamline while-drilling decision-making.New cased-based reasoning technologies can compare the current drilling situation to similar previous case histories where problems occurred. This real-time decision automation enables identification of similar events that led to drilling problems on similar wells drilled in the past. From those historical cases, similar solutions are presented to avoid potential drilling problems before they occur. This while-drilling response provides the automated real-time connection between previous experiences and current operations that reduce drilling risk and ensure greater repeatability.A case history is presented on the use of case-based reasoning to enhance automated advice by identifying hazardous situations in advance that enabled successful corrective action implementation.