{
  "id": 20160426,
  "title": "AI is making software easier to build. Keeping it running is another story",
  "url": "https://urgent.news/2026/11/15/ai-is-making-software-easier-to-build-keeping-it-running-is-another",
  "topic": "ai",
  "section": "AI",
  "published": "2026-11-15T10:00:00.000Z",
  "source": {
    "name": "Fast Company",
    "slug": "fast-company",
    "url": "https://www.fastcompany.com/91642024/ai-is-making-software-easier-to-build-keeping-it-running-is-another-story"
  },
  "original_language": "en",
  "account": "The rapid adoption of AI tools for coding and development is leading to faster software delivery, but maintaining and troubleshooting the software remains a significant challenge. Google's 2025 DORA report indicates that while AI speeds up code creation, it also reduces software stability. This discrepancy highlights the need for companies to invest in AI-driven solutions that can efficiently handle software maintenance and problem-solving. Ishay Yaari, co-founder and CEO of DataAgent, emphasizes that the operational side of software development has not kept pace with the rapid coding advancements. As companies deploy more frequent updates and changes to infrastructure, the potential for failures increases, complicating the already complex task of identifying the root cause and restoring service. Traditional monitoring tools provide alerts but can generate too many that overwhelm engineers, making it challenging to pinpoint and resolve issues promptly. DataAgent's platform aims to autonomously monitor applications and cloud infrastructure, detect potential problems, and assist in their investigation. By combining insights into both the application and its underlying infrastructure, the system can recognize issues that don't fit predefined patterns and even suggest corrective actions. However, assigning AI the authority to make changes in live systems is a significant concern. While AI can identify and propose solutions, determining which changes are safe and appropriate requires human oversight. For instance, deleting large amounts of data or disabling security controls are activities that should only be performed under human supervision to prevent unintended consequences. Companies must carefully define the scope of AI's capabilities, specifying which systems it can access, the types of changes it can make, and when it needs human approval. Additionally, logging all AI-driven actions, particularly failed ones, is crucial for accountability and future improvements. The key to leveraging AI in software maintenance lies in finding the right balance between automation and human intervention. By allowing AI to handle routine, predictable issues while reserving critical decisions for human expertise, companies can streamline their operations and maintain the reliability of their software.",
  "summary": "These days, it almost feels like old news: Developers can now use AI tools to generate code , build features, and make changes in a fraction of the time they once needed. The problem now surfacing across businesses is that once software goes into production, teams still need to monitor, maintain, and fix it. A feature that takes minutes to build can introduce problems that take engineers hours to…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}