IBM Expands Bob With Multi-Agent AI and Enterprise Modernization Workflows

IBM announced major updates to its AI-powered software development platform, IBM Bob, adding multi-agent capabilities, built-in AI cost analytics, and pre-built workflows for enterprise application modernization. The company said the latest release is designed to help engineering teams manage software development beyond code generation by improving review, validation, and modernization tasks.

The announcement comes as organizations increasingly adopt AI-assisted coding tools. IBM cited the 2026 GitLab AI Accountability Report, which found that 85% of surveyed DevSecOps professionals believe AI has shifted the bottleneck from writing code to reviewing and validating it. IBM said Bob provides a unified platform that coordinates AI across the software development lifecycle rather than limiting it to individual coding tasks.

Multi-Agent AI Targets Enterprise Software Development

IBM introduced several new capabilities in Bob, including support for multiple AI agents working together, parallel model-native tool calling, and subagents that isolate complex tasks into separate contexts to reduce execution costs. The company also launched Bobalytics, a built-in analytics feature that provides visibility into AI usage, productivity, model performance, quality, and cost. 

"The bar for enterprise AI is no longer a better coding assistant," Neel Sundaresan, GM, Automation and AI, IBM, said in a statement. "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."

IBM said the platform now optimizes AI execution across different models and agents instead of relying solely on model selection. The company said the approach is intended to help enterprises improve software quality while maintaining oversight of AI spending as deployments scale.

The announcement also builds on IBM's broader enterprise AI strategy, including its work to deploy autonomous AI systems in financial operations.

Premium Packages Focus on Legacy Modernization

Alongside the platform update, IBM introduced three Bob Premium Packages tailored for IBM Z, IBM i, and Java modernization. The packages provide customizable workflows for modernizing legacy applications, including COBOL and PL/I code modernization, JCL analysis, IBM i development environments, and Java migration and dependency analysis.

IBM said the workflows are based on its experience supporting enterprise systems and are designed to deliver repeatable and auditable AI-assisted modernization projects.

The company highlighted customer examples from Jack Henry, where developers used Bob to improve RPG development workflows and code quality, and Blue Pearl, which reported completing a legacy modernization project in three days that had originally been projected to take nine months with 14 engineers.

The latest release reflects a broader shift among enterprise software vendors toward AI platforms that orchestrate complex engineering workflows instead of focusing exclusively on code generation. It also aligns with growing industry attention on managing AI infrastructure costs and governance as organizations expand production deployments, trends reflected in developments such as enterprise efforts to reduce inference costs and the rise of agentic AI platforms.