cp.Discover installs quickly and is pre-configured to find credit card numbers, patient information, and personally identifiable information (PII) used in several countries. Users can also create custom sensitive data types, a feature useful for locating intellectual property and other sensitive data types specific to your business. A single installation of cp.Discover is able to search for information in local and remote file shares, Microsoft SharePoint, and Office 365 without any additional software. cp.Discover uses keywords, regular expressions (patterns), and post-processing (for example, the Luhn Algorithm) to identify sensitive and regulated information. Our classification capability automatically tags and categorizes unstructured data across data centres and clouds. Our solution employs multiple techniques to accurately classify information without compromising system performance or user productivity. - Metadata matching is used to categorize information based on attributes/properties like file type, location, and file owner - Pattern matching is used to find recognizable data such as credit card numbers, medical record numbers, and personally identifiable information - Machine learning (artificial intelligence) is used for information that can be pre-categorised cp.Discover can analyse information on a schedule or be used in-line with existing business process/workflows via an API. It can also be used to automate governance requirements associated with archival and eDiscovery, and enable cloud migrations.