# Launch of DeepSeek’s Harness marks its strategic pivot towards autonomous agentic AI > Source: > Published: 2026-08-14 11:03:52+00:00 # Launch of DeepSeek’s Harness marks its strategic pivot towards autonomous agentic AI With the launch of Harness, China’s DeepSeek continues to build the foundational digital scaffolding for autonomous AI agents [Minxiao Chang](/author/minxiao-chang)in Shenzhen [DeepSeek](https://sc.mp/nae9c?utm_source=copy-link&utm_campaign=3361731&utm_medium=share_widget)is venturing into a new battleground beyond large language models, launching a developer preview of its long-anticipated Harness – a software framework that helps developers turn AI models into autonomous agents. The release on Thursday marks a strategic pivot as DeepSeek moves to build foundational digital scaffolding for AI agents – systems capable of using AI models to operate external software, run code, and complete complex jobs on their own. [earlier beta testing](https://sc.mp/1y5r2?utm_source=copy-link&utm_campaign=3362792&utm_medium=share_widget), taking part developers noted that DeepSeek Harness departed from conventional software tool kits by giving programmers greater control over how their AI agent thinks and acts. Each core element was delivered as a modular plug-in that developers can swap out or combine. Tools like DeepSeek Harness are rapidly becoming an important layer in AI systems, shifting the global competition from model intelligence to one that focuses on how seamlessly an AI agent can connect to real-world software. [DeepSeek hired former Jane Street engineer Cui Tianyu](https://www.scmp.com/tech/big-tech/article/3354113/deepseek-recruits-former-jane-street-engineer-catch-ai-agents-revenue-race?module=inline&pgtype=article?module=inline&pgtype=article)in March to join its newly formed harness group, amid the surging popularity of powerful AI agents like US rival Anthropic’s Claude Code. To cater to different enterprise and developer workloads, DeepSeek Harness provides four operational settings. These include a standard mode for general tasks, a code-focused mode that lets the AI write code to command multiple applications simultaneously, a creative mode that allows the system to experiment with custom tools, and a minimal mode for isolated testing.