Building a successful AI copilot requires a systematic approach. This chapter is divided into two sections, covering the design and evaluation of a copilot, respectively. A case study of developing copilot templates by Microsoft for the retail domain is used to illustrate the role and importance of each aspect. The first section explores the key technical components of a copilot’s architecture, including the LLM, plugins for knowledge retrieval and actions, orchestration, system prompts, and responsible AI guardrails. The second section discusses testing and evaluation as a principled way to manage desired outcomes and unintended consequences of using AI in a business context. We discuss how to measure and improve its quality and safety, through the lens of an end-to-end human-AI decision loop framework. By providing insights into the anatomy of a copilot and the critical aspects of testing and evaluation, this chapter provides concrete evidence of how good design and evaluation practices are essential for building effective, human-centered AI assistants.