IBM updated its IBM Bob agentic software development platform on July 9, 2026, adding multi-agent coordination, built-in cost and usage analytics, and pre-built workflows for modernizing enterprise systems. The changes respond to a shift in enterprise software development: 85% of DevSecOps professionals now say the bottleneck has moved from writing code to reviewing and validating it.
IBM Bob is designed to embed AI across the entire software development lifecycle, not just inside a single coding interface. It provides a unified foundation for teams to coordinate work from initial development through review and deployment. For example, engineers at Jack Henry, a financial services and banking technology provider, used Bob to work with a large, aging RPG codebase. Kevin Sligar, Chief Technical Architect at Jack Henry, said: "Using IBM Bob, our developers are able to accelerate RPG development workflows, improve code quality, and gain deeper insights into decades of accumulated system knowledge while gaining efficiency in enhancement efforts."
Multi-agent execution and cost visibility
Many enterprise teams manually pick AI models, trying to balance cost against performance, and still face inconsistent results and unpredictable spending. Bob now optimizes across the entire execution system rather than just model selection. It matches models to specific tasks, coordinates AI execution across multiple agents, and gives organizations a clear view of productivity, quality, performance, and cost through a new feature called Bobalytics.
The platform also introduces parallel, model-native tool calling, which lets models request several tools in a single turn and run them simultaneously. Subagents handle complex work in isolated contexts, so exploratory steps like file reads and searches don't bloat the context window and drive up costs. Neel Sundaresan, GM, Automation and AI at IBM, said: "Bob is the platform enterprise customers have been asking for. The bar for enterprise AI is no longer a better coding assistant. It's an end-to-end agentic development partner that works inside any system development teams already use, with the governance, security, and cost controls enterprises require. We built Bob to solve the problems enterprises actually have, and the updates we're announcing today are the foundation for everything that comes next."
Pre-built workflows for IBM Z, IBM i, and Java modernization
Moving beyond code generation into large-scale projects like legacy application updates or mainframe modernization introduces variability that can undermine results. Structured, repeatable workflows reduce that risk. IBM Bob now ships with pre-built workflows that teams can customize, ensuring consistent and auditable outcomes regardless of who runs the process.
Blue Pearl, a cloud solutions and consulting services company, tested Bob on a legacy modernization program. Saireshan Govender, Group CEO of Blue Pearl, said: "We introduced IBM Bob to a legacy modernization program, an effort originally projected to take nine months with 14 engineers was completed in just three days. The most powerful outcome wasn't the speed - it was the combination of operational efficiency, cost optimization, and real-world results we could trust and build on."
Premium packages now available
IBM packaged its decades of domain experience into three premium packages that translate institutional knowledge into AI-native workflows:
- IBM Z: AI-native application modernization for mainframe environments, including COBOL and PL/I modernization and JCL analysis. Details here.
- IBM i: AI-native development for IBM i systems, with remote file system integration, IBM i-specific modes and tools, and workflows built around operational patterns of IBM i shops. Details here.
- Java Modernization: AI-guided workflows for Java modernization, including migration to Java 25, large-scale refactoring, and dependency analysis at scale. Details here.
The latest version of IBM Bob is available for download at bob.ibm.com/download. Release details are on the IBM Bob blog.
Why this matters for IT and development professionals
The update directly targets the new reality of AI-assisted coding: the hard work is no longer producing the first draft of code but reviewing, validating, and integrating it at scale. IBM Bob's multi-agent design and cost analytics give teams a way to manage that review burden while keeping spending predictable. For engineers responsible for mainframe, IBM i, or large Java codebases, the pre-built workflows offer a repeatable path to modernization that doesn't require starting from scratch each time. The combination of execution-level optimization and structured workflows means teams can scale AI use without losing control over quality, cost, or auditability.
Your membership also unlocks:
