Meituan Launches CatPaw, a Full-Scenario AI Agent Platform Built on a 1.6T-Parameter Model
CatPaw is one of the first large-scale agent platforms backed by a trillion-parameter model trained on non-Nvidia silicon, and it arrives with internal proof of 90,000 users. For teams evaluating agent infrastructure, it offers a reference architecture that spans personal productivity and enterprise deployment with baked-in domain expertise rather than a blank-slate LLM.
Meituan has released CatPaw, an AI agent platform powered by its LongCat 2.0 model—a 1.6-trillion-parameter system trained entirely on domestic hardware. The platform splits into two parts: a personal AI workbench that runs across mobile, desktop, and cloud, and a managed agent service for building digital employees inside tools like Feishu and WeCom. Agents can autonomously execute tasks like file manipulation, browser control, and terminal commands, delivering finished reports or code.
CatPaw layers Meituan's decade-plus of local commerce data on top of general agent capabilities. Pre-built experts handle domain-specific jobs like store review analysis, marketing copy generation, and operational data diagnostics for food delivery, service retail, and healthcare merchants. Teams can also record their own workflows to create custom skills.
Internally, Meituan already has 90,000 employees using 30,000 agents on the platform. The managed agent tier adds tenant isolation, credential management, hierarchical permissions, and a unified operations dashboard with full session traceability and cost monitoring.
Training a 1.6T model entirely on domestic chips and then immediately productizing it as an agent platform closes the loop from silicon to application in a way most Western labs have not publicly demonstrated.
Bundling domain-specific experts for local commerce—rather than shipping a generic agent builder—signals that the moat for enterprise AI platforms is shifting from model size to vertical data and pre-integrated workflows.
The 30,000-agent internal deployment number is a meaningful signal of platform maturity; it suggests the orchestration, security, and observability layers have been stressed at scale before the public release.
Recording browser actions to generate reusable skills is a pragmatic alternative to purely prompt-based agent configuration and lowers the barrier for non-technical teams to encode institutional knowledge.
The discussion questions whether Meituan's AI agents will actually serve consumer interests. One comment asks for a practical shopping assistant that handles price comparison and order optimization, while a reply counters that the technology is more likely to be deployed for dynamic pricing against users and squeezing more labor from delivery workers.
Can you release an agent that recommends orders? I just wanted to buy a watermelon, and I spent ages searching for merchants, comparing prices, and even adding items to meet the free delivery threshold.