ByteDance debuts Coze Space internal beta for AI agent teamwork
ByteDance has initiated an internal beta for Coze Space, a productivity platform powered by AI that facilitates collaboration between users and AI agents in work environments.
On Friday, ByteDance, the parent company of TikTok, unveiled the internal beta of Coze Space, an AI-driven productivity platform designed to enhance collaboration between users and AI agents in the workplace.
Key Features of Coze Space
- Built on Doubao LLM: The platform leverages ByteDance’s self-developed Doubao large language model and supports the Model Context Protocol (MCP), enabling seamless integration with tools like Lark and Amap.
- Expert Agent System: Coze Space introduces an "Expert Agent" system capable of handling a range of tasks, from answering queries to completing work assignments.
- Multimodal Capabilities: The platform excels in instruction following, tool usage, and multimodal functionalities, making it ideal for scalable deployments.
Development Journey
ByteDance initially explored external models such as DeepSeek-R1 but encountered limitations in tool invocation. After evaluating six Chinese LLMs, the team opted for its in-house Doubao 1.5 Pro model, citing its superior performance in:
- Instruction adherence
- Tool utilization
- Low inference costs
For more details, refer to the original report on Cailian (in Chinese).
Why It Matters
This move underscores ByteDance’s commitment to advancing AI-powered productivity tools, positioning itself as a competitor in the rapidly evolving workspace collaboration sector. The platform’s focus on scalability and cost-efficiency could make it a game-changer for enterprises.
Related News
Lenovo Wins Frost Sullivan 2025 Asia-Pacific AI Services Leadership Award
Lenovo earns Frost Sullivan's 2025 Asia-Pacific AI Services Customer Value Leadership Recognition for its value-driven innovation and real-world AI impact.
Baidu Wenku GenFlow 2.0 Revolutionizes AI Agents with Multi-Agent Architecture
Baidu Wenku's GenFlow 2.0 introduces a multi-agent system for parallel task processing, integrating with Cangzhou OS to enhance efficiency and redefine AI workflows.
About the Author

Dr. Emily Wang
AI Product Strategy Expert
Former Google AI Product Manager with 10 years of experience in AI product development and strategy formulation. Led multiple successful AI products from 0 to 1 development process, now provides product strategy consulting for AI startups while writing AI product analysis articles for various tech media outlets.