Multi-Agent Systems technologies are migrating from research labs to software engineering centres. If these technologies are to realize their potential, it will become increasingly important to develop and employ methodologies, accessible to software engineers, for specifying, analysing, designing, and verifying multi-agent systems. The panelists, who represented a broad range of approaches and experience in MAS theory and practice, addressed the following questions. What can we learn from existing software and knowledge engineering methodologies, such as object-oriented approaches? How can they be adapted and extended to apply to agent-based systems? How should MAS design and specification methodologies address the proliferation of MAS architectures and application environments? Is there any prospect of generic approaches? How important are efforts to standardize various aspects of MAS technology? What techniques and tools are needed to support agent-oriented design and development? What approaches, formal and practical, will allow us to verify and diagnose large-scale MAS applications? What can we learn from related domains, such as real-time and distributed systems?.