At a three‑day Thoughtworks summit in Engelberg, senior engineers agreed that AI‑driven code generation has become abundant, while the true bottleneck now lies in verification, governance, and maintaining human judgment across legacy modernization, token economics, and organizational practices.
The article presents a step‑by‑step AI‑enhanced workflow for modernising legacy systems, explaining how OpenSpec’s spec‑driven requirement layer and Superpowers’ strict execution pipeline (brainstorming, isolated worktrees, TDD, code review) together resolve inaccurate demand understanding and uncontrolled code generation, with a concrete flash‑sale implementation and practical pitfalls.
This article explores how generative AI, integrated into intelligent IDEs, can accelerate the analysis, redesign, and migration of legacy systems by providing scenario‑driven code enhancement, automated testing, custom actions, and living documentation, while also addressing validation and customization challenges.
