{
  "id": 724501,
  "title": "I Joined 10+ Hackathons During My Maternity Leave. Here’s What Happened.",
  "url": "https://urgent.news/2026/08/13/i-joined-10-hackathons-during-my-maternity-leave-heres-what-happened",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-08-13T02:39:07.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/_6bb3445a3dec/i-joined-10-hackathons-during-my-maternity-leave-heres-what-happened-43na"
  },
  "original_language": "en",
  "account": "For the past three months, the author has been on maternity leave while preparing for a significant life change. Despite this, she managed to participate in over ten hackathons, a goal she did not initially plan. As each project took shape, deadlines followed, leading to a collection of completed work she never anticipated.\n\nThe author worked during whatever free time she could find, tackling tasks ranging from fixing bugs to improving features. Some sessions resulted in complete projects, while others involved fixing small issues or understanding API errors. This routine was not perfect, but it was effective for her.\n\nOne of the author's latest projects, QuoteX, was developed for the Global AI Hackathon with Qwen Cloud. QuoteX is an AI agent designed for cross-border commerce. In her technical article, \"I Gave Qwen Six Tools, but Not the Right to Set a Price,\" the author explains how QuoteX works. A user can describe a product using text, voice, or an image, and Qwen understands the request, plans the workflow, and selects the necessary tools. However, the author made an important architectural decision: the AI cannot invent a price. Pricing, policy checks, and commercial calculations are handled by deterministic services, with a human approving the final quotation before it can be sent.\n\nTo test this architecture, the author conducted 42 adversarial scenarios. The governed system, like QuoteX, passed all 42, while a direct AI baseline only passed 28. Through this experience, the author learned several valuable lessons. Building a functional AI demo is different from creating a trustworthy product, and presentation matters, but reliability is more critical. Additionally, asking for feedback can be more challenging than writing the code itself. The experience also showed that progress can happen even during ordinary responsibilities and in short, tiring sessions.\n\nThe author is eager for honest feedback on QuoteX. She wants to know if the boundary between AI reasoning and business authority is clear, if users would trust this architecture in a real commercial workflow, and what improvements she should make next.",
  "summary": "For the last three months, I have been on maternity leave and preparing for a major change in my life. I also participated in more than ten hackathons. I did not plan to enter so many. I wanted to keep learning, build a few ideas, and use this time to challenge myself. Then one project became another, one deadline followed the next, and suddenly I had a collection of things I never expected 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."
}