On the evening of October 31, the DeepSeek Harness team published a technical article titled "Super-agent Design Exploration: Toward More Autonomous Agent Systems." The article notes that advances in model capabilities have spawned new application forms, with personal assistants (Personal Agents) recently emerging in concentrated fashion. However, existing mainstream Agent designs treat a single Session as the basic unit, with different Sessions operating independently of one another—making it difficult to support multitasking and team collaboration at scale. As a result, the upper limit for a single task depends on model capability, while the upper limit for multiple tasks depends on human attention. To address this, the team sought to break through these limitations through ideas such as a dual-layer architecture, event-driven design, asynchronous multi-channel interaction, separation of storage and computation, and an external Watchdog. The system takes over tedious session management and context synchronization at the underlying level, freeing humans to move up from execution details to higher-level decision-making and acceptance. DeepSeek calls this Agent form and its system architecture Super-agent. At present, an internal Super-agent instance built on this approach has been running continuously, routinely participating in problem reproduction and fixes, code review responses, and iteration of DeepSeek Harness itself.