DXC and LangChain advance an agent-based AI framework for critical IT operations
This partnership combines DXC’s decades of experience operating critical enterprise systems with LangChain’s technology for securing AI agent frameworks.
DXC OASIS, built on the open-source LangChain LangGraph runtime, is expanding to 125 customer environments across regulated industries and multiple regions.
Across 500 test cases, OASIS reduced resolution time by an average of 95% and achieved diagnostic accuracy of 92% or higher.
Ashburn, Virginia, October 13 (PRNewswire)—DXC Technology (NYSE: DXC) today announced a partnership with LangChain, the company behind the open-source LangGraph agent framework and LangSmith agent engineering platform. The two companies will advance governed agent-based AI for critical enterprise IT environments.
This partnership builds on DXC’s use of LangGraph within DXC OASIS, OASIS being DXC’s intelligent orchestration platform and operating model for critical IT operations. DXC is also licensed to use LangSmith to support the development, evaluation, and observability of OASIS agents. OASIS is already in production and is being expanded to 125 customer environments across regulated industries and multiple regions. Both parties state that these capabilities enable DXC to build, orchestrate, evaluate, and continuously improve AI agents while applying the necessary enterprise context, governance, human oversight, and ongoing assurance in critical operational environments.
Introducing agent-based AI into mission-critical operations
Through this partnership, DXC is leveraging LangGraph and LangSmith to advance the construction, orchestration, evaluation, and continuous improvement of OASIS agents. LangGraph provides an open-source framework for agent orchestration, including capabilities such as delegation, state management, and human-in-the-loop workflows; LangSmith offers tools for agent development, evaluation, and observability.
OASIS integrates these capabilities into enterprise IT operations, enabling agents to respond to operational events, investigate issues in parallel, invoke specialized capabilities across technology domains, and involve human personnel when judgment or approval is required. DXC states that this allows human experts to focus on higher-value decisions, while agents provide the capacity and speed needed to handle large-scale operational issues. In specific production use cases, file system events that previously took 53 to 90 minutes to resolve are now addressed in 3 to 6 minutes; database performance events are reduced from 2 to 3 hours to 5 to 12 minutes; and complex problem management that once required 2 to 6 days is now completed in 8 to 10 minutes.
Dan Gray, President of Global Infrastructure Services at DXC Technology, said: “Agent-based AI has the potential to fundamentally transform how enterprises operate their most critical technologies, but models alone are not enough. Based on more than 500 use cases, OASIS reduced resolution times by an average of 95% and achieved diagnostic accuracy of 92% or higher when validated against expert engineer judgments. Through our partnership with LangChain, we are combining advanced agent technology, operational expertise, and governance to enable AI agents to operate safely at enterprise scale.”
Scale agentive AI under governance and human oversight
A key focus of this partnership is helping businesses scale the use of AI agents while maintaining appropriate governance and human oversight. With LangChain technology, OASIS now enables agents to operate within defined permissions while preserving the control required in mission-critical environments. Actions are evaluated based on factors such as reversibility, impact, verifiability, and the agent’s past performance. Sensitive operations can be paused before execution pending human approval; meanwhile, agent decisions, tool calls, and outcomes are tracked to provide clear visibility into how the agent operates.
OASIS also enables agents to reason based on their specific enterprise environment. Agents can access system-specific and customer-specific information, DXC operational expertise, and vendor documentation to make judgments tailored to the context and requirements of each customer environment, rather than relying solely on general model knowledge. DXC states that by integrating enterprise context with defined governance policies and human oversight, OASIS allows organizations to expand the role of AI agents in production environments while maintaining accountability and control.
Julia Schottenstein, Chief Operating Officer of LangChain, said: “Agents are reshaping the application layer of every enterprise, and leading companies are taking control of their own agent technology stacks. This means tailoring frameworks to their specific business needs, grounding agents in proprietary context, and establishing governance and continuous improvement loops to ensure agents operate reliably in production environments. We are excited to bring this model to critical enterprise operations through our partnership with DXC.”
An Open Path to Enterprise-Agent AI
This partnership also supports an open, agent-based AI approach designed to give businesses flexibility and control as AI technologies evolve. OASIS is not tied to a single model and enables interoperability with third-party and customer-owned systems, allowing organizations to select different models for various workloads based on requirements such as quality, cost, latency, and privacy. OASIS is also designed to continuously improve during operation, leveraging insights from agent execution to enhance performance and incorporating lessons learned from individual scenarios into the broader system over time.
Deployment can cover public cloud, private cloud, dedicated environments, and sovereign environments without requiring a redesign of the underlying architecture. Customers retain control over their data, workflows, and operational capabilities built on the platform, while maintaining flexibility across models, infrastructure, and deployment environments.
DXC and LangChain detail their approach in a new technical whitepaper, “DXC OASIS: The Harness for Mission-Critical IT Operations,” exploring how organizations can deploy AI agents in mission-critical environments while maintaining governance, accountability, and human oversight.
About DXC Technology
DXC Technology (NYSE: DXC) is a leading enterprise technology and innovation partner that provides software, services, and solutions to global enterprises and public sector organizations, helping them drive outcomes through AI in an era of rapid change. With deep expertise in managed infrastructure services, application modernization, and industry-specific software solutions, DXC modernizes, secures, and operates some of the world’s most complex technology systems. Learn more at dxc.com.