World Congress 2026 Europe • Jul 10, 2026 • Session details

Building with IBM Bob

Maximilian Jesch

Can an AI agent safely untangle decades-old legacy code? Discover how IBM Bob goes beyond simple autocomplete to securely modernize enterprise architecture and automate CI/CD workflows.

Pause
Mute Enter Fullscreen
#1 about 3 min

Overview and internal adoption of IBM Bob

Widespread internal adoption proves the practical effectiveness of IBM's custom AI coding assistant.

#2 about 2 min

Exploring a sample codebase using the agent

Exploring a sample application codebase demonstrates live issue resolution and backlog management capabilities.

#3 about 2 min

Creating explicit and persistent implementation plans

Generating a detailed, persistent plan before writing code improves agent determinism and output quality.

#4 about 5 min

Building custom skills to interrogate planning gaps

Creating a custom interrogation skill resolves ambiguities in generated implementation plans through clarifying questions.

#5 about 2 min

Persisting logic documents to drive code generation

Combining original requirements with generated planning artifacts triggers automated implementation logic more reliably.

#6 about 1 min

Monitoring agent activity with custom analytics dashboards

Tracking language usage, repository interactions, and credit consumption maintains tight cost control over coding agents.

#7 about 2 min

Restricting autonomous actions with specific agent modes

Enforcing system permissions and scoped personas restricts an agent's read, write, and deployment capabilities securely.

#8 about 3 min

Automating code commits and pull request workflows

Leveraging agentic workflows creates cohesive commit messages and generates standardized pull requests without manual intervention.

#9 about 4 min

Headless terminal automation for code review pipelines

Executing the agent from a terminal interface via GitHub Actions enables automated, deterministic code reviews.

#10 about 4 min

Modernizing massive legacy mainframe and IBM i codebases

Integrating specialized premium packages with static code analysis provides the context needed to modernize highly verbose enterprise applications.

#11 about 4 min

Automating Java version migrations with rule-based recipes

Combining deterministic OpenRewrite scripts with agentic testing capabilities seamlessly migrates outdated Java services.

#12 about 1 min

Encouraging developer experimentation and targeted workflow customization

Implementing custom workflow tooling and behavior primitives empowers developers to build highly tailored automation.

Matching moments

6:35 min

Modernizing legacy COBOL mainframe systems using AI agents

Chris Heilmann Chris Heilmann +2 · LIVE

1:02 min

Multi-agent AI for migrating legacy COBOL to Java

Julia Kordick Julia Kordick · World Congress 2025

3:23 min

Migrating legacy COBOL systems using generative AI tools

Chris Heilmann Chris Heilmann +9 · LIVE

2:46 min

Deploying AI agents for enterprise legacy code modernization

Neel Sundaresan Neel Sundaresan +1 · World Congress 2026 Europe

3:03 min

Evaluating AI agents for iterative legacy code modernization

Michael Friedrich Michael Friedrich · World Congress 2026 Europe

2:15 min

Leveraging artificial intelligence to accelerate system migration

Annette Schelten Annette Schelten +1 · World Congress 2025