Agentic AI for IBM i DevOps: Develop faster and maintain Control
Your management wants AI. Your developers are already experimenting with it. And your auditors want to know who approved what.
For IBM i teams, the pressure is real, but so are the stakes: your applications run critical business processes, and a change that “almost works” can be costly.
AI coding agents are fast, but they are probabilistic, their costs are unpredictable, and they will try to work around any rule written in a prompt. So how do you let them help without losing control of quality, security, and accountability?
In this session, we’ll walk through a real IBM i scenario, from a developer’s request to an AI agent all the way to UAT. You’ll see where AI saves time and where a deterministic, governed process must take over.
Key takeaways
- Where AI really helps IBM i developers, and where it adds risk
- How to keep humans accountable and changes traceable
- How to avoid costly AI tokens and hallucinations
- How to get started, even if your team isn’t on Git or DevOps yet
Live demo featuring VS Code, Claude, ARCAD for DevOps, and DROPS.
Speaker

Alan Ashley
Solution Architect, ARCAD Software
Alan has been in support and promotion of the IBM i platform for over 30 years and is the Presales Consultant for DevOps on IBM i role with ARCAD Software. Prior to joining ARCAD Software, he spent many years in multiple roles within IBM from supporting customers through HA to DR to Application promotion to migrations of the IBM i to the cloud. In those roles, he saw first hand the pains many have with Application Lifecycle Management, modernization, and data protection. His passion in those areas fits right in with the ARCAD suite of products.
