{
  "id": 15725937,
  "title": "I let agents plan a WNBA finals trip (but kept my wallet to myself)",
  "url": "https://urgent.news/2026/10/20/i-let-agents-plan-a-wnba-finals-trip-but-kept-my-wallet-to-myself",
  "topic": "business",
  "section": "Business",
  "published": "2026-10-20T09:00:05.000Z",
  "source": {
    "name": "Axios",
    "slug": "axios",
    "url": "https://www.axios.com/2026/10/20/battle-of-bots-openai-meta-ai-agents-test"
  },
  "original_language": "en",
  "account": "The Battle of the Bots, part 1, is an exploration of AI assistants Dots and Muse as they were put through their paces in planning a WNBA Finals trip to Atlanta. The testing ground for these AI agents is significant as companies rush to develop digital assistants capable of handling everything from shopping to travel planning. However, there remains a gap between the capabilities of these agents and what users are comfortable entrusting to them. The agents were asked to plan a fantasy trip to Atlanta, organize a themed brunch watch party, and create souvenir programs. They were also tasked with assisting in shopping for WNBA merchandise, which led to a side quest for WNBA basketball cards. Muse, which is free with optional subscriptions, and Dots, which requires a paid subscription or enterprise plan, both performed impressively in handling complex, multistep assignments. They both found good flight options, though they faced challenges with ticket sales and scheduling conflicts. Muse created a colorful recipe booklet for the purple-themed brunch but required minor edits, while Dots produced a more practical packet with detailed instructions. Both agents designed invitations that needed aesthetic tweaks. The AI agents were also asked to create a 1980s-style WNBA Finals souvenir program and turn game photos into a keepsake. Dots produced a more visually engaging program, while Muse's version, though less attractive, contained fun touches. Both programs contained questionable statistics, with Muse subsequently correcting errors. When it came to actually making purchases, Dots excelled, while Muse struggled. Both agents could have done more if given greater access to the reporter's accounts and wallet. The reporter, however, is not yet comfortable authorizing purchases or trusting the agents with consequential decisions. In conclusion, for now, the most effective use of these AI agents is in doing research and legwork, with the final decisions left to the user.",
  "summary": "Let's call it the Battle of the Bots, part 1: I decided to put two of the newest personal AI agents, OpenAI's Dots and Meta's Muse , through their paces, with the WNBA Finals providing a natural testing ground. Why it matters: AI companies are racing to create the digital assistant we turn to for everything from shopping to travel planning. But there's still a gap between what these agents can do…",
  "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."
}