We’re excited to announce the general availability of IBM watsonx Assistant for Z - a new generative AI assistant that brings conversational AI and IT automation together to transform the way system programmers, IT operators, and developers of all experience levels engage with and manage the mainframe.
IBM watsonx Assistant for Z enhances IBM Z professionals’ productivity by putting decades of experience and best practices at your teams’ fingertips. This AI assistant is designed to simplify and optimize the execution of repeated tasks by codifying the knowledge of Z experts into a trusted set of automations that can be used by system programmers, operators and developers of all experience levels. IBM watsonx Assistant for Z improves IBM Z users’ autonomy and confidence by providing accurate answers that help reduce the time to onboard early-tenure users and accelerate knowledge transfer from Z experts.
Built upon IBM watsonx Orchestrate and in partnership with IBM Research, watsonx Assistant for Z uses a chat-focused granite-13b-chat-v2 model. This model is an enterprise-level English-language model that is meticulously trained with an extensive dataset of over 2.5 trillion tokens, including IBM Z-specific content. This model is backed by a Z domain-specific retrieval-augmented generation (RAG), a technique that allows to augment large language models with knowledge from additional sources. The Z domain specific RAG provides accurate answers and current information that leverages IBM Z domain-specific knowledge.
IBM watsonx Assistant for Z is designed to simplify and optimize the execution of repeated tasks by codifying knowledge into a trusted set of automation assets. Users can seamlessly import existing trusted automation created with Ansible, JCL, and REXX, among others as skills into the product catalog. These skills can be invoked via a contextually aware chat experience, using watsonx Orchestrate’s extensible automation framework that improves productivity and accelerates efficiency on the mainframe.
To get started with watsonx Assistant for Z, visit the product webpage and sign up for a live demo.
Khadija Souissi, principal product manager - AI for IBM Z
Scott Engleman, special projects and product management - IBM Z
Allison Gaynor, Go-to-market PM team lead , Z application modernization