Agentic AI on the Mainframe, Greater Delivery Flexibility, and more

Jan 20, 2026

Sonja Soderlund is an Oregon-based B2B freelance writer. Whether writing about mainframe computers, educational technology, or sustainable retail, she strives to bring clarity to complex issues. Connect with her or LinkedIn.

Agentic AI for Smarter Mainframe Modernization with IBM watsonx Code Assistant for Z

IBM has announced the 2.8 release of watsonx Code Assistant for Z, its AI-powered, end-to-end modernization tool for mainframe developers and architects. The update reflects broader industry momentum toward agentic AI, with IBM Institute for Business Value research projecting AI-enabled workloads to grow from 3% in 2024 to 25% by 2026.

Key updates in the 2.8 release include:

  • Unified agentic experience: Previously separate capabilities are now converged into a single, intuitive workflow designed to accelerate modernization and reduce risk.
  • Prompt-driven, multi-step tasks: Developers can initiate complex actions, such as updating Db2 tables or refactoring monolithic code, using natural language prompts.
  • Automated analysis and validation: The agentic workflow identifies dependencies, performs impact analysis, generates standards-compliant code, and completes build and compile verification.
  • MCP-based toolset: Built on the Model Context Protocol (MCP), the solution integrates with mainframe-specific tools for metadata retrieval, impact analysis, code generation, and documentation.
  • Improved documentation generation: New capabilities address decades of fragmented or missing documentation by producing scalable, business-aware application insights.
  • Business Rule Discovery: Designed for large, complex Z applications, this feature delivers precise, intent-aligned explanations with code-aware segmentation.
  • Client-context enrichment: Integration with data dictionaries and business glossaries ensures outputs reflect enterprise-specific terminology and meaning.

Together, the 2.8 release positions watsonx Code Assistant for Z as a more integrated and practical modernization solution for enterprises with complex mainframe environments. By combining agentic workflows, deeper system awareness, and business-context enrichment, IBM is aiming to help organizations modernize faster, reduce risk, and extend the value of their existing applications while preparing for more AI-driven operations.

Source: IBM

The Open Mainframe Project’s Zowe 3.4 

As part of the journey to modernize and open up the mainframe ecosystem, Open Mainframe Project’s Zowe 3.4 introduces a wave of improvements, refinements, and foundational updates that aim to make enterprise development and operations smoother, more transparent, and easier to contribute to.

The Zowe 3.4 release brings major simplification to the configuration and operations on the server side:

  • The API Mediation Layer fully supports and by defaults uses authentication directly with SAF instead of through z/OSMF.
  • The API Mediation Layer changes by default and runs as a single service adding less operational overhead and making it easier to understand potential issues.
  • The configuration scripts use far more JCL instead of shell scripts in backend.

To take a look at what’s new and what’s coming next, read the summary of key changes and plans in this Medium article or you can watch the full recording of the system demo and planning, available on Zoom.

Zowe 3.4 is available to download via zowe.org/download, through the relevant marketplaces for Explorer for VS Code and Explorer for Intellij.

Precisely Achieves FedRAMP Authorization

Precisely has announced that the Precisely Data Integrity Suite has achieved FedRAMP® Moderate Impact Level authorization and is now officially listed on the FedRAMP Marketplace. The certification from the Federal Risk and Authorization Management Program (FedRAMP) applies to the Suite’s Data Governance Service.

With over 475 authorized service offerings listed on the FedRAMP Marketplace, the federal government continues to build momentum in cloud and SaaS adoption with a growing emphasis on robust and standardized security frameworks. The inclusion of Precisely among these authorized providers strengthens its position as a trusted partner to federal agencies looking to securely and efficiently modernize data governance in the cloud, with a solution that advances data integrity, transparency, and compliance across all levels of government.

Secure, Collaborative Data Governance for the Government Sector

The Data Integrity Suite provides agencies with the essential capabilities to securely access, catalog, and manage critical data. As part of the Suite, the Data Governance Service delivers a trusted environment where users can modernize their data governance initiatives and scale their data integrity journey, strengthening collaboration, visibility, and compliance across programs.

It provides a flexible, no-code framework that helps establish clear ownership, policies, and workflows, making it easier for teams to collaborate and manage data with confidence. 

“Government sector organizations have long faced the challenge of managing sensitive data scattered across a complex, hybrid environment with numerous legacy and cloud-based systems,” said John Guedel, Vice President of Government, Precisely. “By achieving FedRAMP authorization, Precisely is helping government agencies overcome those barriers, resulting in greater collaboration, accountability, and faster decision-making, enabling these organizations to achieve data integrity at scale.”

Source: Precisely

0 Comments

Submit a Comment

Your email address will not be published. Required fields are marked *

Sign up to receive the latest mainframe information

This field is for validation purposes and should be left unchanged.

Read More

❓ History of Artificial Intelligence Trivia

❓ History of Artificial Intelligence Trivia

November at Planet Mainframe is all about AI, and you don’t need us to tell you that artificial intelligence has now been integrated into many of our daily routines. But long before AI became a household term, IBM was shaping the foundations of this increasingly...