DXC and LangChain scale governed agents in mission-critical IT operations
DXC OASIS combines LangGraph orchestration and LangSmith evaluation and observability with human approval, authority limits, and audit trails.
AT A GLANCE
Key points
- Combines LangGraph orchestration with LangSmith observability
- Sensitive actions can pause for human approval
- DXC says it is scaling toward 125 customer environments
- Performance rates come from DXC's own measurements
What is changing?
DXC Technology and LangChain announced a partnership on October 13 to expand governed AI agents in mission-critical enterprise IT. DXC OASIS already uses the LangGraph runtime; the agreement also licenses LangSmith for agent development, evaluation, and observability.
OASIS agents can respond to events, investigate issues in parallel, and bring people into the process when judgment or approval is required. Authority is bounded by factors including reversibility, impact, verifiability, and an agent's track record. Tool calls and outcomes are traced for audit visibility.
DXC says the platform is scaling toward 125 customer environments and has reduced resolution time by an average of 95 percent across more than 500 measured use cases, with diagnostic accuracy of at least 92 percent against senior engineer judgment. These are company measurements, not independent results.
Explore the original sources
Source date: 13 October 2026.
Published by AI Radar: 14 Oct 2026, 00:11 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.
Loading comments…