> Markdown version of [/videos/100275-building-with-ibm-bob](https://www.wearedevelopers.com/videos/100275-building-with-ibm-bob). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Building with IBM Bob

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.

- **Speakers:** [Maximilian Jesch](https://www.wearedevelopers.com/@maximilian-jesch)
- **Event:** World Congress 2026 Europe
- **Published:** July 10, 2026
- **Duration:** 28:28
- **URL:** https://www.wearedevelopers.com/videos/100275-building-with-ibm-bob

## Summary

Modern software development demands efficiency in both greenfield projects and legacy system modernization. IBM Bob is an AI coding agent utilized internally by over 120,000 IBMers, designed to augment the developer workflow from planning to execution. Operating as a flexible agent rather than just an autocomplete tool, Bob integrates seamlessly into daily programming practices to manage software complexity thoughtfully.

The core philosophy of leveraging this AI assistant effectively revolves around rigorous, explicit planning and custom scoping. Best practices dictate that developers persistently save and refine structural plans before writing any actual code. To assist with this, platform abstractions include "skills" (on-demand prompt augmentations, such as interrogating a proposed tech spec for edge cases) and "modes" (persona-based contexts that enforce precise file-access permissions, like a read-only Code Reviewer). Furthermore, exploring the headless terminal interface allows teams to script and automate pull request reviews directly within CI/CD pipelines via GitHub Actions.

Crucially, the assistant tackles the 68% of IT budgets tied up in maintaining legacy applications. Enterprise deployments offer specialized packages tailored to Mainframes (COBOL), IBM i architectures, and complex Java migrations. Instead of relying on generic and unpredictable agentic rewrites, the workflow merges traditional rule-based operations—such as OpenRewrite recipes for upgrading a Java 8 service to Java 21—with deep AI evaluation mapping. This synthesis ensures that testing, functional validation, and infrastructure documentation are generated with deterministic predictability, providing a reliable safety net for heavy-duty system overhauls.

**Keywords:** ibm bob AI assistant, agentic coding workflows, software architecture planning, custom prompt skills, persona-based AI modes, headless terminal automation, github actions CI/CD, pull request automation, legacy code modernization, mainframe COBOL migration, ibm i architecture, java version upgrades, openrewrite recipes, developer usage analytics, shift-left security

## Chapters

1. **Overview and internal adoption of IBM Bob** (00:00) — Widespread internal adoption proves the practical effectiveness of IBM's custom AI coding assistant.
1. **Exploring a sample codebase using the agent** (02:50) — Exploring a sample application codebase demonstrates live issue resolution and backlog management capabilities.
1. **Creating explicit and persistent implementation plans** (04:10) — Generating a detailed, persistent plan before writing code improves agent determinism and output quality.
1. **Building custom skills to interrogate planning gaps** (05:31) — Creating a custom interrogation skill resolves ambiguities in generated implementation plans through clarifying questions.
1. **Persisting logic documents to drive code generation** (10:20) — Combining original requirements with generated planning artifacts triggers automated implementation logic more reliably.
1. **Monitoring agent activity with custom analytics dashboards** (11:40) — Tracking language usage, repository interactions, and credit consumption maintains tight cost control over coding agents.
1. **Restricting autonomous actions with specific agent modes** (12:25) — Enforcing system permissions and scoped personas restricts an agent's read, write, and deployment capabilities securely.
1. **Automating code commits and pull request workflows** (14:02) — Leveraging agentic workflows creates cohesive commit messages and generates standardized pull requests without manual intervention.
1. **Headless terminal automation for code review pipelines** (16:54) — Executing the agent from a terminal interface via GitHub Actions enables automated, deterministic code reviews.
1. **Modernizing massive legacy mainframe and IBM i codebases** (20:05) — Integrating specialized premium packages with static code analysis provides the context needed to modernize highly verbose enterprise applications.
1. **Automating Java version migrations with rule-based recipes** (23:54) — Combining deterministic OpenRewrite scripts with agentic testing capabilities seamlessly migrates outdated Java services.
1. **Encouraging developer experimentation and targeted workflow customization** (27:35) — Implementing custom workflow tooling and behavior primitives empowers developers to build highly tailored automation.

## Related Moments

- [Modernizing legacy COBOL mainframe systems using AI agents](https://www.wearedevelopers.com/videos/1365-wearedevelopers-live-the-weekly-developer-show-with-chris-heilmann-and-daniel-cranney) (from " WeAreDevelopers LIVE - the weekly developer show with Chris Heilmann and Daniel Cranney")
- [Multi-agent AI for migrating legacy COBOL to Java](https://www.wearedevelopers.com/videos/1531-migrating-from-cobol-with-ai-a-moonshot-demo) (from "Migrating from COBOL with AI: A Moonshot Demo")
- [Migrating legacy COBOL systems using generative AI tools](https://www.wearedevelopers.com/videos/1766-devs-vs-marketers-cobol-and-copilot-make-live-coding-easy-and-more-the-best-of-live-2025-part-3) (from "Devs vs. Marketers, COBOL and Copilot, Make Live Coding Easy and more - The Best of LIVE 2025 - Part 3")
- [Deploying AI agents for enterprise legacy code modernization](https://www.wearedevelopers.com/videos/100256-can-this-elephant-dance-ibm-bob-and-the-future-of-ai-first-software-development) (from "Can This Elephant Dance? IBM Bob and the Future of AI-First Software Development")
- [Evaluating AI agents for iterative legacy code modernization](https://www.wearedevelopers.com/videos/100320-when-agents-meet-legacy-never-change-a-running-system) (from "When Agents Meet Legacy: Never Change a Running System")
- [Leveraging artificial intelligence to accelerate system migration](https://www.wearedevelopers.com/videos/1444-crew-management-system-for-airlines-plan-duties-for-pilots-flight-attendants-worldwide) (from "Crew Management System for Airlines: Plan duties for pilots & flight attendants worldwide")

## Related Articles

- [What is Agentic Programming and Why Should Developers Care?](https://www.wearedevelopers.com/magazine/625-what-is-agentic-programming-and-why-should-developers-care)
- [How we Build The Software of Tomorrow](https://www.wearedevelopers.com/magazine/120-how-we-build-the-software-of-tomorrow)
- [Transforming Software Development: The Role of AI and Developer Tools](https://www.wearedevelopers.com/magazine/527-transforming-software-development-the-role-of-ai-and-developer-tools)
- [GitHub Copilot: Beyond the Basics – 10 Ways to Elevate Your Coding](https://www.wearedevelopers.com/magazine/524-github-copilot-beyond-the-basics-10-ways-to-elevate-your-coding)

## Related Jobs

- [Principal Product Manager, Agent Platform](https://www.wearedevelopers.com/jobs/ext/277541-principal-product-manager-agent-platform) at **GitHub**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [Principal Software Engineer, Enterprise AI Platform](https://www.wearedevelopers.com/jobs/ext/1467292-principal-software-engineer-enterprise-ai-platform) at **GitHub**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**
- [Senior Software Engineer, Enterprise Products](https://www.wearedevelopers.com/jobs/ext/1841248-senior-software-engineer-enterprise-products) at **GitHub**
- [Tribe Lead - ( Software) Engineering Centre of Excllence](https://www.wearedevelopers.com/jobs/ext/1475530-tribe-lead-software-engineering-centre-of-excllence) at **SD Worx**