United StatesTechnology and telecom2024 – ongoingIBM
Generative AI assistant for IBM Z questions and incident resolution
IBM's CIO organization cut incident resolution time by 10% with a generative AI assistant for its mainframe teams
Problem
More than 100 new and early-tenure professionals joined the CIO Organization in two years. They needed to learn the IBM Z mainframe environment and often searched for answers by hand.
Approach
The team deployed watsonx Assistant for Z on-premises on an existing Red Hat OpenShift cluster. It uses retrieval-augmented generation over curated IBM Z content to answer questions and suggest fixes for incidents. More than 300 users used it, and more use cases were planned.
Results
Takeaway
Grounding the assistant in curated platform content gave newer staff a faster route to answers than searching on their own.
Categories
- Size
- Large enterprise
- Industry
- Technology and telecom
- Business function
- IT and R&D
- Innovation type
- Process innovation
- AI technology
- Generative AI
- Adoption
- Built in-house
- Evidence
- Vendor case study
Sources
Source summaries
The page covers IBM's internal CIO Organization using watsonx Assistant for Z to support IBM Z staff. It reports an 8% cut in learning time and 10% faster incident resolution. It also reports a 50% drop in Db2 patching time from automation, and over 300 users.
Full details are in the original sources.