DXC Technology has announced a strategic partnership with LangChain-the creator of the open-source LangGraph agent framework and the LangSmith engineering platform-to scale governed agentic artificial intelligence across mission-critical enterprise IT environments.
The alliance centers on integrating LangGraph and LangSmith into DXC OASIS, an intelligent orchestration platform and operating framework for enterprise IT operations. DXC is also licensing LangSmith to streamline the development, testing, evaluation, and observability of AI agents across its global service delivery network. Currently deployed and expanding toward 125 active customer environments in highly regulated industries worldwide, DXC OASIS pairs autonomous execution with enterprise context, regulatory compliance, and continuous human-in-the-loop oversight.
Accelerating Incident Resolution with Agentic Workflows
The integration of LangGraph’s open-source orchestration suite makes it possible for OASIS agents to take advantage of sophisticated capabilities, such as autonomous delegation of tasks, complex states handling, and immediate human intervention. LangSmith helps developers with tooling, evaluation, and monitoring of agent performance.
Also Read: Boomi and Jade Global Expand Partnership to Accelerate Governed AI Agent Adoption Across Manufacturing Operations
OASIS offers agentic abilities within ordinary IT operations, which makes it possible for agents to monitor operational events, conduct investigation alongside other tools, and delegate difficult decisions to humans if required. In this way, senior engineers will be able to spend their time on architecture decisions, while AI agents will take care of operational events.
Enterprise Governance, Context, and Human Oversight
One of the basic tenets of the DXC and LangChain partnership involves guaranteeing safe operation of AI agents in mission-critical environments. Instead of running freely without regulation, OASIS uses a risk assessment process that takes into account the effects, reversibility, previous execution history, and criticality of each proposed action by the AI agent.
Any high-risk or non-reversible administrative commands are automatically halted until they are approved by a human. Every single tool invocation, decision path, and output generated by the AI agent is tracked via LangSmith.
To eliminate model hallucination and generic responses, OASIS grounds agents in specific operational environments. Agents draw real-time telemetry from system documentation, vendor knowledge bases, customer-specific runbooks, and DXC’s proprietary operational data, ensuring all reasoning reflects the precise requirements of each enterprise footprint.
“Agentic AI has the potential to fundamentally change how enterprises operate their most critical technology, but models alone are not enough,” said Dan Gray, President, Global Infrastructure Services, DXC Technology. “Across more than 500 measured use cases, OASIS has reduced resolution time by 95% on average, with diagnostic accuracy of 92% or better when validated against senior engineer judgment. Through our work with LangChain, we’re bringing together advanced agent technology, operational expertise, and governance to put AI agents to work safely at enterprise scale.”
“Agents are transforming the application layer for every business, and the enterprises pulling ahead are taking ownership of their agent stack,” said Julia Schottenstein, Chief Operating Officer, LangChain. “That means adapting the harness to their business, grounding agents in proprietary context, and building the governance and continuous improvement loops that make agents reliable in production. We’re proud to bring that model into mission-critical enterprise operations through our partnership with DXC.”
Model-Agnostic and Flexible Hybrid Infrastructure
The collaboration promotes an open architecture, which enables enterprises to avoid any risk of model lock-in. DXC OASIS is model agnostic and provides integration capability with third-party, commercial, and customer-owned LLMs. The capability makes it possible for IT organizations to allocate appropriate AI models to individual workload types depending on factors such as cost, latency, specialization, and privacy needs.
Besides, OASIS implementation may cover the public cloud, private cloud, on-premise data center, and sovereign cloud environments without any code changes to the underlying software. The customers have total ownership of their data and processes while enjoying learning loops.
