September 25, 2024 By Allison Gaynor
Scott Engleman
3 min read

Imagine your mainframe users having accurate, curated responses to all their questions instantly at their fingertips. What if your system programmers and operators could perform both routine and complex tasks correctly every time, with minimal reliance on subject matter experts? That’s the transformation IBM watsonx™ Assistant for Z aims to deliver.

IBM watsonx Assistant for Z is a generative AI assistant launched at Think 2024 earlier this year. This AI assistant uniquely combines conversational artificial intelligence (AI) and IT automation to revolutionize how your Z users engage with and manage the mainframe. It helps organizations reduce the learning curve for early-tenure professionals, boosts productivity, autonomy and confidence for all Z users, and accelerates knowledge transfer by enabling experts to codify their Z knowledge.

Building on this momentum, today we are excited to announce new product capabilities and enhancements to IBM watsonx Assistant for Z, including:

  • Ingest your own enterprise documentation, making it easier to find answers for internal applications and processes.
  • Prebuilt skills (automations) provided for common IBM® z/OS® tasks, accelerating time to value.
  • Simplified architecture for ease of deployment and cost effectiveness.

Ingest you own enterprise documentation

Every organization operates differently, with unique processes, applications, technologies and workflows. Many of these processes have been refined over the years, with a few experts constantly being interrupted for the most basic questions.

With IBM watsonx Assistant for Z, you now have the flexibility to customize the Z RAG, ingesting your own documentation and best practices. Personalizing your Z RAG offers greater autonomy for your Z users, who can now get curated answers tailored specifically to your organization’s environment, processes and internal knowledge.

Builders can use a command-line interface (CLI) to ingest proprietary and third-party documentation such as PDF, DOCX, HTML and text at scale into the retrieval augmented generation (RAG). Because the RAG is on-premises and behind the firewall, there is no concern that your proprietary content can be compromised.

What is RAG and its relevance in IBM watsonx Assistant for Z?

IBM watsonx Assistant for Z uses a chat-focused granite.13b.labrador model and a Z domain-specific RAG that can be enhanced with your enterprise data. Using the RAG with the large language model (LLM) brings added value in the form of accurate and context-rich responses to complex queries, leading to answers that include references to sources and significantly reducing the opportunity for hallucinations for both IBM Z® products and your internal applications, processes and procedures.

Learn more on RAG

Prebuilt skills for faster time to value

Organizations can use prebuilt skills available for common z/OS tasks. This means you can seamlessly integrate automations, such as display all subsystems, checking the installation date of a program temporary fix (PTF) or verifying a product release level running on a system, into an AI assistant without specialized expertise, enabling your Z users to use them easily.

Also, your IBM Z experts can build complex automations and skill flows for unique use cases faster by using prebuilt skills, accelerating time to value.

Simplified architecture for deployment ease and cost effectiveness

Organizations are no longer required to use IBM watsonx™ Discovery, previously necessary for supporting elastic search. Instead, they can take advantage of the built-in OpenSearch, which merges keyword and semantic searches to access the Z RAG. This enhancement not only improves response quality but also significantly lowers the cost of owning IBM watsonx Assistant for Z and simplifies the deployment.

Get started with IBM watsonx Assistant for Z

IBM watsonx Assistant for Z is designed to help your Z users with accurate and up-to-date answers to their Z queries and simplifies the execution of repeated tasks by codifying knowledge into a trusted set of automations. To discover more about how it can help your organization, schedule a live demo with an IBM expert.

Schedule a live demo with an IBM expert

Resources:

More from Artificial intelligence

IBM launches Mistral AI with IBM, enabling customers to deploy Mistral AI’s most powerful foundation models on premises with IBM watsonx

2 min read - Foundation modes are trained on billions of parameters of data, but most of this data is general purpose and from the public domain. While useful in some scenarios, enterprises must often train these base foundation models on their own proprietary data, a step called “fine-tuning.” Tuning helps to maximize a model’s productivity in terms of overall accuracy for any specific use case. Given the potentially sensitive nature of this data and an organization’s data security standards, uploading proprietary data to a…

How a solid generative AI strategy can improve telecom network operations

3 min read - Generative AI (gen AI) has transformed industries with applications such as document-based Q&A with reasoning, customer service chatbots and summarization tasks. These use cases have demonstrated the impressive capabilities of large language models (LLMs) in understanding and generating human-like responses, particularly in fields requiring nuanced language understanding and inferencing. However, in the realm of telecom network operations, the data is different. The observability data comes from proprietary sources and encompasses a wide variety of formats, including alarms, performance metrics, probes…

How AI is making electric vehicles safer and more efficient

4 min read - Over 250,000 electric vehicles (EVs) were sold every week last year globally, according to a recent survey from the International Energy Agency. The survey also found that consumer adoption is at a tipping point, with industry executives expecting EVs to account for 40% of car sales by 2030, largely due to EVs becoming cheaper. The battery is the single biggest contributor to the cost of EVs—and a hotspot for concerns around safety and performance. But new research from the University…

IBM Newsletters

Get our newsletters and topic updates that deliver the latest thought leadership and insights on emerging trends.
Subscribe now More newsletters