What is Mainframe Assessment Tool?
Mainframe Assessment Tool is a Google Cloud service that, per the documentation, is meant to accelerate the end-to-end journey from an existing mainframe setup to resources on Google Cloud. Users upload a zip file (up to 400 MB) containing their mainframe application code; the tool automatically scans the code using generative AI and delivers detailed assessment results on technology stack and dependencies.
Per the documentation, supported programming languages are COBOL, JCL, HLASM, BMS, RPG/RPGLE, Easytrieve, and Natural for z/OS; PL/I, REXX, Fortran, and UniVerse BASIC carry preview status. On the data side, the tool recognizes DB2, IMS DB, Adabas, and QSAM and VSAM datasets, along with the CICS and IMS DC transaction monitors and the BMC Control-M scheduler.
The tool groups mainframe assets into sequenced, migratable units based on call and data dependencies, extracts business rules from the code, and generates AI-produced documentation. Per the documentation, the migration journey is organized into three phases: discover and assess, plan migration, and migrate workloads.
The tool runs on a self-created Compute Engine VM or GKE cluster in your own project; access happens through an Identity-Aware Proxy tunnel to localhost. The “Keep data in my region” setting restricts model calls to a specific multi-region endpoint, documented for the EU as aiplatform.eu.rep.googleapis.com.
Core Features
- AI-powered code analysis: Automated evaluation of uploaded mainframe codebases using generative AI, including optional detailed summaries and test-case generation.
- Broad language support: COBOL, JCL, HLASM, BMS, RPG/RPGLE, Easytrieve, and Natural for z/OS as established formats; PL/I, REXX, Fortran, and UniVerse BASIC as preview.
- Dependency mapping: Groups assets into migratable units based on call and data dependencies.
- Business rule extraction: Automated extraction of business rules from existing mainframe code.
- Self-hosted deployment: Runs on your own Compute Engine VM or GKE cluster, accessed via an Identity-Aware Proxy tunnel.
- Optional EU data residency: Via “Keep data in my region” using the EU multi-region endpoint
aiplatform.eu.rep.googleapis.com.
Typical Use Cases
Assessing an existing mainframe landscape
Organizations upload their COBOL or PL/I code to automatically capture technology stack, dependencies, and modernization effort before making a migration decision.
Prioritizing migration waves
Dependency mapping groups applications into migratable units, making it easier to sequence a phased migration.
Documenting legacy knowledge
AI-powered extraction of business rules and automated documentation preserves existing domain knowledge before it is lost with retiring mainframe specialists.
Migrations with EU data residency requirements
With the “Keep data in my region” option and the EU multi-region endpoint, the assessment can run without model calls leaving the EU.
Benefits
- Automated, AI-powered analysis saves time compared to manual code review.
- Broad coverage of common mainframe languages, databases, and transaction monitors.
- Free to use for Google Cloud migrations; only the resources consumed are billed.
- EU data residency option for customers with such requirements.
Integration with innFactory
As a certified Google Cloud Partner, innFactory supports you in using Mainframe Assessment Tool: setting up the Compute Engine or GKE environment, configuring EU data residency, interpreting assessment results, and deriving a prioritized migration plan.
Contact us for advice on your mainframe modernization.
Typical Use Cases
Frequently Asked Questions
What is Mainframe Assessment Tool?
Mainframe Assessment Tool is a Google Cloud service that, per the documentation, accelerates the end-to-end journey from an existing mainframe setup to resources on Google Cloud. It automates the analysis of uploaded mainframe codebases using generative AI and delivers detailed results on technology stack and dependencies as a basis for migration planning.
Which programming languages and technologies are supported?
Per the documentation, supported languages include COBOL, JCL, HLASM, BMS, RPG/RPGLE, Easytrieve, and Natural for z/OS; PL/I, REXX, Fortran, and UniVerse BASIC carry preview status. On the data side, the tool recognizes DB2, IMS DB, Adabas, and QSAM and VSAM datasets, plus the CICS and IMS DC transaction monitors and the BMC Control-M scheduler.
How much does Mainframe Assessment Tool cost?
Per the official pricing page, the tool itself is free for migrations to Google Cloud. You pay only for the resources it requires, such as Compute Engine instances, the Gemini Enterprise Agent Platform, storage, and network traffic. Per the pricing page, there is currently no SLA for the tool itself.
How does EU data residency work?
The tool runs on a self-managed Compute Engine VM or GKE cluster in a zone you choose. The "Keep data in my region" option restricts model calls to the assessment region and its multi-region without a global fallback; for the EU, the documentation names the multi-region endpoint aiplatform.eu.rep.googleapis.com. Without an external IP address on the instance, a Private Service Connect endpoint targeting the matching multi-region endpoint is additionally required.
Note: All product information on this page has been compiled with care, but is provided without guarantee and may be outdated or incomplete. Cloud services evolve rapidly — features, pricing, SLAs, and availability change frequently. Authoritative and up-to-date information can only be found on the official product page of Google Cloud (official documentation). This page does not represent an offer by Google Cloud.
