DXC and LangChain Advance Agentic AI Harnesses for Mission-Critical IT Operations

Customers retain control of their data and workflows while OASIS supports different AI models and deployment environments.

Rhea-AI Summary

DXC Technology (NYSE: DXC) announced a partnership with LangChain to advance governed AI agents across mission-critical enterprise IT environments.

The partnership builds on DXC OASIS, its IT operations platform, which uses LangChain's open-source LangGraph framework. DXC is also licensing LangSmith for agent development, evaluation and monitoring. OASIS is in production, and DXC says it is scaling toward 125 customer environments across regulated industries and multiple geographies. Across 500 measured use cases, OASIS reduced resolution time by 95% on average, with diagnostic accuracy of 92% or better when validated against senior engineer judgment.

News Explained

The release describes added governance controls for OASIS agents: actions are assessed for factors such as reversibility and impact, sensitive actions can be held for human approval, and agent decisions and tool calls are traced.

Key Figures

Customer environments: 125 customer environments Measured use cases: more than 500 use cases Average resolution-time reduction: 95% +4 more

Customer environments

125 customer environments

OASIS is in production and scaling toward this deployment level

Measured use cases

more than 500 use cases

OASIS production use cases measured

Average resolution-time reduction

95%

Across more than 500 measured use cases

Diagnostic accuracy

92% or better

Validated against senior engineer judgment

Filesystem incident resolution

53-90 minutes to 3-6 minutes

Reported production use cases

Database performance incident resolution

2-3 hours to 5-12 minutes

Reported production use cases

Complex problem management

2-6 days to 8-10 minutes

Reported production use cases

Key Terms

human-in-the-loop, observability, model agnostic

3 terms

human-in-the-loop technical

"including capabilities such as delegation, state management, and human-in-the-loop workflows"

Human-in-the-loop describes systems where people supervise, check, or make final decisions on work performed by automated tools or algorithms. Like a pilot overseeing an autopilot, humans step in to catch errors, interpret nuance, and apply judgment that machines may miss. For investors, this matters because human oversight can reduce operational and regulatory risk, improve decision quality, and increase trust in results produced by automated systems.

observability technical

"LangSmith to support the development, evaluation, and observability of OASIS agents"

Observability is a company’s ability to see and understand what its software systems are doing by collecting and analyzing signals like logs, metrics and traces. For investors it matters because strong observability reduces the risk of downtime, hidden bugs or security issues, supports faster fixes and efficient scaling, and therefore can protect revenue, lower costs and signal disciplined operations — like having clear gauges and alarms on a complex machine.

model agnostic technical

"OASIS is model agnostic and supports interoperability with third-party and customer-owned systems"

An approach, tool, or method that is model agnostic can be applied to, or used with, any predictive or analytic model without requiring changes to that model’s internal structure or assumptions. In practice this means the technique operates using a model’s inputs and outputs (for example, predictions, probabilities or feature values) rather than its internal parameters, so it can explain, evaluate or augment different kinds of models (linear, tree-based, neural networks, etc.). Limitation: because it treats models as black boxes, a model-agnostic method may provide less detailed or less efficient information than techniques designed specifically for a particular model class.

AI-generated analysis. How Rhea-AI works. Not financial advice.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

• Partnership brings together DXC's decades of experience operating mission-critical enterprise systems with LangChain's technology for safely and securely managing AI agent harnesses
• DXC OASIS, built on LangChain's open-source LangGraph runtime, is scaling toward 125 customer environments across regulated industries and multiple geographies
• Across 500 measured use cases, OASIS has reduced resolution time by 95% on average, with diagnostic accuracy of 92% or better

ASHBURN, Va., Oct. 13, 2026 /PRNewswire/ -- DXC Technology (NYSE: DXC), a leading enterprise technology and innovation partner, today announced a partnership with LangChain, the company behind the open-source LangGraph agent framework and LangSmith agent engineering platform, to advance governed agentic AI across mission-critical enterprise IT environments.

The partnership builds on DXC's use of LangGraph within DXC OASIS, its intelligent orchestration platform and operating model for mission-critical IT operations. DXC is also licensing LangSmith to support the development, evaluation, and observability of OASIS agents. OASIS is already in production and scaling toward 125 customer environments across regulated industries and multiple geographies. Together, these capabilities help DXC build, orchestrate, evaluate, and continuously improve AI agents while applying the enterprise context, governance, human oversight, and continuous assurance required for critical technology environments.

Bringing Agentic AI Into Mission-Critical Operations

Through the partnership, DXC is using LangGraph and LangSmith to advance how OASIS agents are built, orchestrated, evaluated, and continuously improved. LangGraph provides the open-source framework for agent orchestration, including capabilities such as delegation, state management, and human-in-the-loop workflows, while LangSmith provides tooling for agent development, evaluation, and observability.

OASIS integrates these capabilities to enterprise IT operations, enabling agents to respond to operational events, investigate issues in parallel, draw on specialized capabilities across technology domains, and bring people into the process when judgment or approval is required. This allows human experts to focus on higher-value decisions while agents provide the capacity and speed to address operational issues at scale. Across specific production use cases, filesystem incidents that previously took 53-90 minutes can be resolved in 3-6 minutes, while database performance incidents have moved from 2-3 hours to 5-12 minutes. Complex problem management that previously required 2-6 days has been reduced to 8-10 minutes.

"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."

Scaling Agentic AI with Governance and Human Oversight

A core focus of the partnership is helping enterprises expand the use of AI agents while maintaining appropriate governance and human oversight. Using LangChain technology, OASIS now enables agents to operate within defined authority while maintaining the controls required for mission-critical environments. Actions are assessed based on factors including reversibility, impact, verifiability, and an agent's track record. Sensitive actions can be paused for human approval before execution, while agent decisions, tool calls, and outcomes are traced to provide visibility into how agents operate.

OASIS also grounds agents in the specific enterprise environments in which they operate. Agents can draw from system-specific and customer-specific information, DXC operational expertise, and vendor documentation, helping them reason using the context and requirements of each customer environment rather than relying solely on general model knowledge. By combining this enterprise context with defined governance policies and human oversight, OASIS enables organizations to expand the role of AI agents in production while maintaining accountability and control.

"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."

An Open Approach to Enterprise Agentic AI

The partnership also supports an open approach to agentic AI designed to give enterprises flexibility and control as AI technologies evolve. OASIS is model agnostic and supports interoperability with third-party and customer-owned systems, enabling organizations to select different models for different workloads based on requirements including quality, cost, latency, and privacy. OASIS is also designed to continuously improve as it operates, using insights from agent executions to improve performance and incorporate lessons from individual scenarios into the broader system over time.

Deployments can span public cloud, private cloud, dedicated, and sovereign environments without requiring a redesign of the underlying architecture. Customers retain control of their data, workflows, and the operational capabilities they build on top of the platform, while preserving flexibility across models, infrastructure, and deployment environments.

DXC and LangChain detail their approach in a new technical white paper, DXC OASIS: The Harness for Mission-Critical IT Operations, which explores how organizations can operationalize AI agents while maintaining governance, accountability, and human oversight across mission-critical environments. 

About DXC Technology

DXC Technology (NYSE: DXC) is a leading enterprise technology and innovation partner delivering software, services, and solutions to global enterprises and public sector organizations — helping them harness AI to drive outcomes at a time of exponential change with speed. 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 estates. Learn more on dxc.com.

View original content to download multimedia:https://www.prnewswire.com/news-releases/dxc-and-langchain-advance-agentic-ai-harnesses-for-mission-critical-it-operations-302906323.html

SOURCE DXC Technology Company

FAQ

AI-generated questions and answers. How Rhea-AI works. Not financial advice.

How does DXC OASIS maintain human oversight of AI agents?

DXC OASIS can pause sensitive actions for human approval before execution. Actions are assessed for reversibility, impact, verifiability and the agent's track record. Agent decisions, tool calls and outcomes are traced to provide visibility into their operation.

What deployment environments does DXC OASIS support?

DXC OASIS deployments can span public cloud, private cloud, dedicated and sovereign environments without redesigning the underlying architecture. The platform supports different AI models and interoperability with third-party and customer-owned systems.