Follow the latest coverage, related explainers and connected technology stories.
Microsoft explains through a series of four sessions how an application based on IChatClient becomes an agent capable of using tools, files, memory, and code execution, with controls for approval, monitoring, evaluation, and deployment. The series highlights that running an agent in a production environment requires permission isolation and clear governance, not merely the addition of new capabilities.
Uno Platform describes its experience building two servers for the Model Context Protocol: one to provide AI agents with up-to-date documentation, and another to interact with a running .NET application and verify its interface. The experience highlights that code generation is only half the task, while building a reliable application requires giving the agent live context, inspection tools, and clear procedures.