Enterprise Knowledge Search · IT Operations Automation
IBM’s CIO Organization needed to help new and early-tenure professionals manage IBM Z environments more independently because the mainframe skill curve was steep and subject matter experts were spending too much time answering routine questions, handling incidents, and guiding patching work.
Reported impact
The CIO Organization shortened onboarding, sped incident resolution and Db2 patching, and gave hundreds of users a more confident way to operate IBM Z without as much reliance on scarce experts.
IBM CIO deployed watsonx Assistant for Z as an on-premises generative AI and automation layer for mainframe operations. Running on an existing Red Hat OpenShift cluster, the assistant uses curated IBM Z knowledge and retrieval-augmented generation to answer product and operational questions, helping newer staff get digestible guidance without waiting for senior experts. The team also prioritized incident analysis and Db2 patching as early use cases: watsonx Assistant for Z can ingest incidents from a third-party workflow automation platform, suggest actions based on documentation and similar past events, and interact with Ansible-based automation plus change-management workflows to open, route, and close patching requests. This turns the assistant from a Q&A bot into an orchestration surface for routine mainframe operations. Because the CIO organization iterated with the product team during rollout, the deployment also improved the product itself while giving IBM a reusable pattern for bridging mainframe skills gaps with grounded AI plus operational automation.
User questions and incidents enter watsonx Assistant for Z, RAG grounds responses in curated IBM Z content, incidents are enriched with historical and workflow-platform context, and the assistant can trigger Ansible-backed automations and change requests before reporting status back to the operations user.
“10% faster resolution of incidents”
“300+ users are using watsonx Assistant for Z”
“50% decrease in time to patch Db2 systems”
“The model used by IBM watsonx Assistant for Z addresses a common cause of potential hallucinations by leveraging Retrieval Augmented Generation (RAG) architecture”
“deployed watsonx Assistant for Z on-premises on an existing Red Hat OpenShift cluster.”
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
IBM Sample Jan 15, 2026 IBM IBM needed to reduce the time employees spent on repetitive work across HR, procurement, IT, supply chain, tax, and sales while creating a repeatable enterprise blueprint for scaling AI, automation, and hybrid-cloud… 15K AI agents proposed by employees during the 2025 IBM watsonx Challenge IBM Apptio · IBM Turbonomic · IBM Watson Discovery 
Anthropic Sample Archived · Aug 30, 2026 Atlassian Atlassian wanted agents to do consequential work inside Jira, Confluence, and related products, but enterprise customers would only trust long-running automation if the models could follow complex instructions, use… 5 million+ agents executed in customer business workflows each month Claude Code · Claude Platform · Rovo Chat Anthropic Sample Aug 21, 2026 Notion Notion needed to embed trusted Claude agents natively inside collaborative workflows, with automations, long-running tasks, memory, coding sandboxes, and human approvals that could scale across whole workspaces instead… 12 hours of prototyping work collapse into about 20 minutes Claude Managed Agents 