AI Architecture · Dependencies and deployment

AI Stack Builder
Build the stack. Connect the solution.

Start with a preferred architecture, or configure from your requirements or existing infrastructure. Each component brings its own dependencies, checked against a curated catalogue of deployment paths.

Experimental tool · Not vendor-endorsed · Illustrative configurations only

Your AI architecture

Transactional AI shares processors and z/OS across MLz/model, zDLC, and larger application boxes. Supporting selections remain in the review. Hover or focus to bring a component forward.

Inspect a component

Each block is an individual component. Its dependencies are checked within its assigned deployment stack.

Review stacks, dependencies, and hand-offs
Maintain the catalogue

The component catalogue, deployment profiles, rules, and preferred presets drive this tool. Import catalogue JSON to try a different catalogue in this browser. Configuration export includes the active catalogue, so it can be transferred with your selections.

The tool enforces a curated catalogue of deployment paths and architecture rules. “Outside this profile” means unavailable in this catalogue, not necessarily technically impossible. Documented paths and authored design rules are distinguished. Product releases, model operators, hardware sizing, licences, and security controls require deployment validation.

IBM, IBM Z, LinuxONE, Telum and Spyre are trademarks or registered trademarks of IBM Corporation. Red Hat and OpenShift are trademarks or registered trademarks of Red Hat, Inc. or its subsidiaries in the United States and other countries. Linux is the registered trademark of Linus Torvalds in the U.S. and other countries. All other product names and trademarks are the property of their respective owners. References are for identification purposes only and do not imply sponsorship or endorsement.