From Legacy to Agile:
How AI is Transforming IBM Power Application Modernisation

5th May 2026BlogTom Richards

Are you ready to get in touch?

Request a Call back

IBM Power Systems have kept businesses running for decades. But the applications sitting on those platforms are under growing pressure to modernise, and the specialist skills needed to do it safely are in short supply. In this piece, Tom Richards sets out why AI is changing what’s possible, and what IBM Power customers should be thinking about before the window for managed, planned modernisation starts to close.

For many organisations, IBM Power Systems, running IBM i (formerly AS/400) or AIX, represent decades of mission-critical investment. The applications they support have processed millions of transactions, underpinned entire business models, and quietly kept the lights on for industries ranging from manufacturing and distribution to financial services and the public sector.

But the world around those platforms has changed dramatically, and the pressure to modernise is now acute. Agile development cycles, cloud integration, API-first architectures, and modern user experience expectations are hard to reconcile with applications written in RPG or COBOL across multiple decades of iterative development, often with little documentation and fewer people who understand them deeply.

The question for most IBM Power customers is no longer whether to modernise, but how to do it without disrupting the operations that depend on those systems every day. Increasingly, AI is changing the answer to that question.

The question is no longer whether to modernise IBM Power applications, it's how to do it without disrupting the operations that depend on them every day. Share on X

The legacy problem: more complex than it looks

IBM i and AIX applications are often described as legacy, but that word understates the challenge. These aren’t simply old systems; they are deeply embedded systems. Business logic has accumulated over thirty, sometimes forty years, with rules, exceptions, and workarounds baked into the code that no single person fully understands anymore. In many cases, the original developers have retired or moved on. Documentation, where it exists at all, is incomplete, inconsistent, or simply wrong.

The result is what practitioners sometimes call a ‘black box’ problem. The application works — and critically, the business depends on it working — but the organisation cannot safely change it, extend it, or connect it to modern systems without significant risk. Every modification becomes an exercise in archaeology, and every release carries the anxiety of unintended consequences.

The technical debt compounds over time. As regulatory requirements evolve, as customer expectations shift toward digital-first experiences, and as integration with cloud platforms becomes a commercial necessity, the cost of maintaining that status quo rises. Modernisation ceases to be optional.

Developer reviewing legacy code during IBM Power application modernisation analysis

The skills crisis is accelerating the urgency

IBM i and AIX modernisation has always been a specialist discipline. Today, that specialism is becoming critically scarce. The developer community with deep RPG, CL, and COBOL expertise is ageing, and relatively few younger developers are entering those disciplines. The pipeline of skilled resource is narrowing at precisely the moment demand is growing.

This creates a compounding problem for organisations that delay modernisation decisions. The longer they wait, the fewer people will be available to help them when they do act, and the higher the cost of that help will be. In competitive talent markets, experienced IBM i developers command significant premiums, and even at those premiums, capacity is often insufficient to support large-scale modernisation programmes.

At Northdoor, we work with organisations across sectors who are confronting this reality. The skills shortage is not a future risk — it is a present constraint that is already limiting what modernisation programmes can realistically achieve within acceptable timeframes and budgets.

The developer community with deep RPG, CL, and COBOL expertise is ageing. The pipeline of skilled resource is narrowing at precisely the moment demand is growing. Share on X

Where AI changes the equation

The emergence of AI-assisted development tools, and specifically, their application to legacy code analysis, refactoring, and documentation, represents a genuine step change in what modernisation programmes can achieve.

The core capability is this: AI can read, interpret, and reason about legacy code at a scale and speed that no team of human developers could match. What previously required months of manual analysis, mapping business logic, identifying dependencies, understanding data flows, can now be accelerated significantly, enabling modernisation programmes to move faster, with greater confidence, and with a materially reduced dependency on scarce specialist skills.

AI-Assisted Code Analysis and Refactoring

One of the most immediately valuable applications is automated code analysis. AI tools trained on IBM i and AIX environments can ingest RPG, CL, COBOL and associated programmes, map the relationships between them, and produce structured representations of what the application actually does — not what the documentation says it does.

This matters enormously in practice. When modernisation teams begin working on a legacy estate, the first challenge is always understanding scope and complexity. Which modules are interdependent? Where does core business logic reside versus procedural scaffolding? Which code paths are still active, and which are effectively dead? Previously, answering these questions required extensive manual effort from people who understood the codebase intimately, a resource that is increasingly unavailable.

AI-assisted analysis compresses that discovery phase substantially. It also reduces the risk of modernisation decisions being made on incomplete understanding, one of the primary causes of failed or over-budget programmes.

On the refactoring side, AI tools can assist in translating legacy code into modern equivalents, converting RPG programmes to Java or Python, restructuring monolithic applications into modular, API-accessible components, and identifying opportunities to rationalise duplicated logic. Human oversight remains essential; the AI accelerates and augments the work, it does not replace expert judgement. But the productivity gain is significant, and the reduction in dependency on scarce RPG expertise is commercially meaningful.

AI-generated documentation: closing the knowledge gap

Perhaps the most underappreciated capability is automated documentation generation. For organisations with large IBM i estates, the absence of reliable documentation is often the single biggest barrier to confident modernisation,  more limiting, in practice, than the technical complexity of the code itself.

AI tools can analyse legacy programmes and generate structured documentation: functional descriptions of what each programme does, data dictionaries, process flow diagrams, dependency maps, and plain-English explanations of embedded business rules. This documentation serves multiple purposes simultaneously.

It enables modernisation teams, including those without deep legacy expertise, to understand and work with the application. It provides a foundation for testing strategies, ensuring that modernised components can be validated against known expected behaviours. And it creates an institutional knowledge base that the organisation retains, reducing the critical dependency on individual expertise that has left so many IBM Power customers vulnerable.

For organisations that have been operating in a state of knowledge fragility, where the departure of one or two key individuals would represent a genuine operational risk,  this capability alone justifies serious attention.

 

AI can analyse legacy programmes and generate structured documentation, creating an institutional knowledge base that the organisation retains, reducing the critical dependency on individual expertise that leaves so many IBM Power customers vulnerable.

A pragmatic path to IBM i and AIX modernisation

AI-assisted modernisation is not a silver bullet, and it is worth being clear about what it is not. It does not eliminate the need for experienced IBM Power practitioners; it makes them more productive and extends their effective capacity. It does not remove the requirement for rigorous testing and phased delivery; it supports those activities by providing better analysis and documentation as inputs. And it does not make decisions about modernisation strategy; those remain business decisions that require human judgement and commercial context.

What it does offer is a more viable path for organisations that have found modernisation programmes prohibitively complex, slow, or expensive under traditional approaches. It directly addresses the two constraints that most commonly impede progress: the scarcity of specialist skills and the lack of reliable knowledge about the existing estate.

At Northdoor, our approach to IBM Power modernisation combines deep platform expertise with AI-assisted tooling to accelerate analysis, improve confidence in refactoring decisions, and generate the documentation that organisations need to take control of their own applications. We work with clients to develop modernisation roadmaps that are phased, risk-managed, and aligned with operational realities — not programmes that treat modernisation as a single big-bang event.

The case for starting IBM Power modernisation now

IBM Power Systems will continue to run critical workloads for many organisations for years to come — and that is entirely appropriate. The platform’s reliability, performance, and security credentials remain strong. But the applications running on those platforms need to evolve, and the conditions for doing so are becoming simultaneously more urgent and more tractable.

The skills shortage will not reverse. Regulatory and integration pressures will not diminish. The competitive disadvantage of operating applications that cannot connect to modern ecosystems will not shrink. But AI-assisted modernisation tools are now mature enough to make a material difference to what is achievable, at what speed, and at what cost.

For IBM Power customers who have been deferring modernisation decisions, the calculus is shifting. The question is no longer whether the technology exists to support a credible programme — it does. The question is whether organisations are prepared to act before the window of manageable, planned modernisation closes, and reactive crisis management becomes the only alternative.

IBM Power application modernisation: common questions

Organisations approaching IBM Power application modernisation for the first time often underestimate how much the AI-assisted discovery phase reduces overall programme risk.

Q: What is IBM Power application modernisation?

IBM Power application modernisation is the process of updating or replacing legacy applications running on IBM Power Systems, typically IBM i (formerly AS/400) or AIX, so they can meet modern demands around integration, user experience, and agile development. It can involve refactoring existing code, rebuilding components in modern languages, adding API layers, or migrating workloads to hybrid cloud environments.

Q: Why is IBM i modernisation so difficult?

IBM i applications often contain thirty or forty years of accumulated business logic, with limited documentation and few developers who understand them in depth. The original authors have frequently retired, and the specialist skills needed to work safely with RPG, CL, and COBOL are becoming increasingly scarce. That combination of complexity and knowledge fragility makes modernisation genuinely risky without the right expertise and approach.

Q: How does AI help with IBM Power application modernisation?

AI tools trained on IBM i and AIX environments can analyse legacy code at a scale and speed no human team could match. They map dependencies, identify active and dormant code paths, translate RPG or COBOL into modern languages, and generate structured documentation of embedded business logic. This accelerates the discovery and refactoring phases significantly, and reduces the dependency on scarce specialist skills.

Q: Do you still need IBM i specialists if you’re using AI tools?

Yes. AI augments experienced IBM Power practitioners — it does not replace them. The productivity gains are real and commercially meaningful, but human judgement is still essential for modernisation strategy, testing, and delivery. What AI does is extend the effective capacity of the specialists you have and reduce the volume of manual analysis they need to carry out.

Q: What is the risk of delaying IBM Power modernisation?

The longer organisations wait, the fewer specialists will be available to help when they do act, and the higher the cost will be. Regulatory and integration pressures continue to grow, and applications that cannot connect to modern ecosystems become a competitive liability. Planned, phased modernisation is significantly more manageable than reactive modernisation driven by a crisis.

Q: How does Northdoor approach IBM Power modernisation?

Northdoor combines deep IBM Power platform expertise with AI-assisted tooling to accelerate analysis, improve confidence in refactoring decisions, and generate the documentation organisations need to take control of their applications. We develop phased, risk-managed modernisation roadmaps aligned to operational realities, not programmes that treat modernisation as a single big-bang event. Contact us to discuss a structured modernisation assessment.

Ready to assess your IBM Power modernisation options?

Speak to Northdoor’s IBM Power specialists about a structured modernisation assessment.

Contact us 

1

Our Awards & Accreditations