A growing number of devices are used in clinical laboratories resulting in an increase in data volume and diversity. Many devices that find their way to clinical laboratories originate in areas of basic science and lack both device instrumentation and supporting software integrations to be used in clinical settings. In addition, a lack of standards-based analysis tools makes repeatable testing difficult. Even when tools are available, the analysis of results by laboratory technicians is tedious and error prone. It is common practice in laboratories to discard raw, perhaps non-human readable, data once analysis is complete. However, raw data accompanied with analyzed results are required for efforts to AI auto-verification of results. Our teams goal is to develop agent-based approaches to monitor laboratory devices, manage dataflow between systems, to curate raw data repositories to be used in the application of AI to result reporting.