• Assessing internal quality while coding with an agent This article is part of âExploring Gen AIâ. • A series capturing Thoughtworks technologists’ explorations of using gen ai technology for software development. • 27 January 2026 Thereâs no shortage of reports on how AI coding assistants, agents, and fleets of agents have written vast amounts of code in a short time, code that reportedly implements the features desired. • Itâs rare that people talk about non-functional requirements like performance or security in that context, maybe because thatâs not a concern in many of the use cases the authors have. • And itâs even rarer that people assess the quality of the code generated by the agent. • Iâd argue, though, that internal quality is crucial for development to continue at a sustainable pace over years, rather than collapse under its own weight.

Article Summaries:

  • The article examines how an AI coding agent can add GitLab support to CCMenu, a Swift‑based Mac app that displays CI/CD build status. It highlights that while AI assistants can quickly produce feature‑complete code, they rarely address non‑functional concerns such as performance, security, or internal code quality. By integrating the agent into a real‑world codebase, the author observes patterns that suggest AI‑generated code may compromise maintainability over time. The piece argues that sustaining long‑term development requires careful assessment of internal quality, even when using advanced generative tools.
  • Thoughtworks technologists report on using a generative‑AI coding agent to add GitLab support to the CCMenu macOS app, which displays CI/CD build status. The experiment highlights how AI assistants can generate functional code for a Swift codebase, but also underscores the need to scrutinize internal quality-such as code structure, type safety, and maintainability-over time. By comparing the new GitLab API wrappers to existing GitHub‑specific functions, the team observes patterns that suggest AI‑generated code can meet feature requirements yet may introduce subtle quality issues. The memo argues that sustainable development hinges on continuous assessment of internal code quality, not just rapid feature delivery.

Sources: