Skip to Main Content
DBT GPT
Your Favorites

Access your saved pages

Limit Reached
You can favorite up to 50 items. Remove outdated items to make room for new ones.

How RWE Used AI to Modernize a Legacy App in Two Days

A 24-year-old app. No source code. No documentation. See how RWE revived it in two days with AI and human engineering.

RWE Generation Ltd, one of Europe’s leading energy producers, faced a growing operational risk: a number of aging, undocumented applications were running on outdated technology stacks. These systems—many over two decades old—were essential to operating power plants, but impossible to update, scale, or understand without extensive cost, risk, effort and downtime.

To prove the potential of AI-assisted modernization, Publicis Sapient and RWE chose one particularly stubborn application: Tube Tracker. The goal was to show how generative AI, combined with engineering expertise, could transform a critical legacy asset into a modern, maintainable foundation in just days.

Client

RWE Generation Ltd

Services
Technology & Engineering Innovation
Data & Artificial Intelligence
Industry
Energy & Commodities
Start a Conversation

The Imperative for Change

Tube Tracker, a visual interface used to manage pipe systems in RWE’s power plants, was vital for finding damaged infrastructure quickly. However, it was over 24 years old, written in Java, and had no accessible source code, documentation, or experts left to maintain it. In its current form, the application posed not just a technical challenge, but a serious business continuity risk.

The Transformative Solution

Publicis Sapient used Slingshot, our AI platform for software development, to accelerate Tube Tracker's modernization through a five-step process in just two days:

  1. Decompilation: Using open-source AI tools, we converted binary files into readable Java source code—a critical step that modernization simply couldn’t happen without.
  2. Rebuild: We created a modern development environment with Java 17 and PostgreSQL 16, enabling the app to run on current systems for the first time in years.
  3. Refactoring: Sapient Slingshot was used to clean up and restructure the old code, reducing over 7,000 lines to a sleek, readable 5,000, with updated syntax, naming conventions and unit tests.
  4. Business logic extraction: Slingshot analyzed the code to produce entity relationship diagrams and data flow sequences, revealing the app’s core functionality, something no one at RWE could previously access.
  5. Documentation generation: With AI assistance, we created full inline documentation and external README files so future developers can quickly understand and extend the codebase.

At nearly every step, generative AI was paired with human oversight, ensuring code quality, clarity and correctness with an approach that drastically reduced effort and risk.

“I experienced first-hand the accelerated AI-assisted delivery from the Publicis Sapient team, which helped us migrate a 24-year-old application to the latest platform. Beyond the tools, it’s the reimagined end-to-end development process with a human in control that I found impressive—it was a real eye-opener.”

Ryan Brudenell , Head of Digital and IT Solutions, RWE Generation UK Ltd

The Business Impact

The modernization of Tube Tracker saved RWE time, money and future risk exposure:

  • Application revived: What was once a black box is now a living, annotated artifact that can be maintained and rolled out to other RWE sites.
  • Operational continuity restored: Engineers can now deploy, edit and update the app with ease.
  • Risk eliminated: Compliance, security and upgradeability are no longer concerns.
  • A cultural shift sparked: Initial skepticism about AI’s usefulness gave way to cross-organization excitement.

More than just a technical fix, this project redefined what successful modernization looks like. Unlike conventional “black box” AI solutions, Sapient Slingshot offered full transparency, control and collaboration to empower RWE’s team to maintain momentum independently. Publicis Sapient didn’t replace engineers. We made them faster, smarter and more consistent.

Time savings:
35–45 percent in automated code generation
Efficiency gains:
30–40 percent in test creation and unit test setup
Development speed:
1 engineer, 2 days (vs. 2 weeks of manual effort)
Increased confidence:
App now deployable across more sites with zero rework
Lines of code reduced:
From ~7,000 to ~5,000 through clean, modern syntax

“For many enterprise leaders, legacy modernization feels like an impossible tradeoff between cost, risk and agility. This case proves it doesn’t have to be. With Sapient Slingshot, AI became an accelerator, not a gamble, delivering a future-proof solution in days, not months.”

Joana Ristau , Senior Partner & Lead E&C, DACH, Publicis Sapient
Joana Ristau
Joana Ristau
Senior Partner & Lead E&C, DACH

Let's connect

John Nicholson
John Nicholson
Director of Technology, UK

Let's connect

Related reading