DXC and LangChain Enhance AI Agents for Critical IT Operations

DXC Technology has partnered with LangChain to develop and govern AI agents for enterprise mission-critical IT operations. The collaboration focuses on enhancing DXC's OASIS platform, which utilizes LangChain's technology for the secure and efficient operation of these agents.

DXC OASIS, built on LangChain's open-source LangGraph runtime, is already in production and scaling toward 125 customer environments across regulated industries and multiple geographies. The platform aims to significantly accelerate IT issue resolution. According to company reports, OASIS has reduced resolution times by an average of 95% and improved diagnostic accuracy to 92% or better when validated against senior engineer judgment.

The partnership's objective is to integrate AI agents into business-critical IT services in a secure and controlled manner. LangGraph provides the framework for agent orchestration, including state management and human-in-the-loop workflows. LangSmith supports the development, evaluation, and observability of agents. This allows human experts to focus on more complex decisions while agents handle routine tasks requiring rapid response.

DXC emphasizes that beyond the models, enterprise-specific context, governance, and human oversight are necessary for the widespread adoption of AI agents in critical environments. OASIS integrates these elements, ensuring agents operate within defined authorities and controls. The solution aims to increase flexibility and control as AI evolves, allowing the use of different models for various tasks based on quality, cost, and privacy considerations.