Use Case Intelligence RSS Search use cases Search
Anthropic Commercial and Professional Services United States Company newsroom

DXC Technology

IT Operations Automation

DXC needed to build a production-scale agentic operations platform for managed services where specialized AI agents could coordinate complex enterprise IT workflows while meeting enterprise security, compliance, reliability, and accessibility requirements and reducing friction in design, debugging, and delivery.

Read the original story Explore all use cases
20% to 30%
8–10 mins time to close problems, down from 2–6 days
95% first-time response accuracy
more than 60 customers

Reported impact

Business outcome

DXC OASIS went live in April 2026 and was already deployed to more than 60 customers. DXC says Claude made OASIS software delivery ten times faster, enabled more than 95% of code generation before human review, and helped the platform achieve strong early operational results across IT use cases.

  • Productivity Improvement
  • Scalability
  • Speed to Market

Solution

DXC built DXC OASIS as an AI-native operations platform for managed services using Anthropic’s Claude during development and architecture design. Engineers used Claude Code plus Opus and Sonnet to turn requirements into code, generate UI mockups from DXC OASIS design components, diagnose failures, and reason through supervisor-versus-sub-agent behavior, interruption handling, and load and security trade-offs. In the deployed platform, DXC OASIS uses a unified data foundation to give specialized AI agents shared context, then orchestrates handoffs among agents such as server administration, ITSM, and observability agents. Incident details and telemetry are pulled into this shared context layer so the appropriate agent can act or delegate, while users consume results through a chat interface. The platform was designed for enterprise security, compliance, reliability, and production-scale IT operations.

Data flow

Enterprise IT signals, incident details from ITSM, and telemetry from observability systems feed DXC OASIS’s unified data foundation. Supervisor logic uses that shared context to route work to specialized agents such as server administration, which hand off tasks and return results through the platform’s chat interface.

Solution architecture

7 components · 4 layers
  1. Ingest
    • ITSM agent It provides incident details to other agents operating within DXC OASIS.
    • observability agent It supplies telemetry data that other agents use for diagnosis and task execution.
  2. Compute
    • Claude Code DXC used it to generate code, accelerate debugging, and turn approved designs into implementation artifacts.
    • Opus DXC evaluated and used it to accelerate architectural reasoning and engineering work on the platform.
    • Sonnet DXC evaluated and used it alongside Opus as a default model for engineering productivity and problem solving.
  3. Orchestration
    • DXC OASIS The AI-native orchestration platform coordinates specialized agents to run managed-services workflows at production scale.
  4. Uncategorized
    • server administration agent It handles delegated infrastructure administration tasks within the multi-agent workflow.

Architecture clues

  • DXC describes a unified data foundation that gives every AI agent the context it needs to act and delegate tasks autonomously.
  • DXC subjected DXC OASIS to production-style security and reliability testing, including edge cases such as slow responses and agent handoffs.
  • Early results were reported across 56 IT use cases.
  • The coordination layer had to define supervisor and sub-agent boundaries, task routing, interruption handling, and behavior under load.
  • The platform uses dozens of specialized AI agents that hand off tasks and share context.

Evidence from the source

"Across 56 IT use cases, DXC OASIS hits 95% first-time response accuracy and cuts average resolution time by ~95%."
"Across the full build, DXC estimates that Claude made OASIS software delivery ten times faster, with more than 95% of code generated by Claude before human review."
"An agent managing enterprise IT infrastructure knows exactly when to call in a server administration agent, tap an IT Service Management (ITSM) agent for incident details or query an observability agent for telemetry data."
"DXC OASIS is built on a unified data foundation that gives every AI agent the context it needs to act and delegate tasks autonomously."
"Problems that consumed two to six days are now closed in eight to ten minutes."
Transparency Evidence & methodology 100/100 reference value · 100% confidence · 3 sources

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value100/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact25/25
    6 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence100%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability25/25
    12 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency10/10
    3 source references document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. DXC Technology

    How DXC Technology used Anthropic’s Claude to build DXC OASIS, an agentic operations platform | DXC Technology Insights

    First-party
    https://dxc.com/insights/knowledge-base/article/how-dxc-used-claude-to-build-dxc-oasis-agentic-operations-platform
    Source type
    Customer-published story
    Published
    Oct 13, 2026
    Supports
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • Business outcome
    • Metrics
    • Architecture
    • Publication date
  2. Built In

    DXC Technology Careers, Perks + Culture | Built In

    Independent secondary
    https://builtin.com/company/dxc-technology

    The Organization JSON-LD lists addressLocality 'Ashburn', addressCountry 'US', and numberOfEmployees value 86261.

    Source type
    Structured company profile
    Supports
    • Company size
  3. DXC Technology

    Board of Directors | DXC Technology

    First-party
    https://investors.dxc.com/governance/board-of-directors/default.aspx

    The page directs communications to DXC Technology Company at 20408 Bashan Drive, Suite 231, Ashburn, VA 20147, United States.

    Source type
    Company governance page
    Supports
    • Region

Date evidence

  • Published on source page Oct 13, 2026 · DXC Technology · First-party
    Open date source

Related

Similar use cases

See all like this
OpenAI Oct 8, 2026 Endava Commercial and Professional Services Global Endava needed to remain relevant in an AI-centric market by redesigning software delivery and cross-functional workflows, not just adding point tools to existing engineering processes. 11,000-person global workforce Application RefactoringIT Operations Automation AI agents · ChatGPT Enterprise · Codex ServiceNow Modified · Oct 7, 2026 Thrive Commercial and Professional Services Boston, Massachusetts Thrive needed a scalable managed-services operating model for SMB customers, but repetitive ticket triage, fragmented customer collaboration, and slow access to context were consuming engineer time and delaying issue… 21,000 hours of manual work saved Customer Service AutomationIT Operations Automation AI Agents · AI Control Tower · Action Fabric Google Cloud Archived · Oct 2, 2026 PT Astra Graphia IT Commercial and Professional Services Indonesia AGIT needed to scale a managed security operations center that could meet Indonesian data-residency requirements, reduce noisy alert handling, and standardize detection engineering for enterprise customers. AGIT scales its enterprise Managed SOC in Indonesia using Google SecOps, Gemini, and Mandiant to drive 15%… IT Operations AutomationSecurity and Compliance Cloud Run · Compute Engine · Gemini