Study finds AI shopping agents fail nearly half of purchase tasks
11/05/2026 — 11/05, 21:20·1 sources (all)·1 reports (all)
Key takeaways
- A first-of-its-kind experiment reported by Fortune asked agents including Gemini and Muse to complete real shopping tasks such as buying TVs…
Background & analysis
On November 5, 2026, Fortune reported on a first-of-its-kind experiment in which AI agents such as Gemini and Muse were tasked with carrying out shopping assignments, including buying a TV and a laptop. The point was to test how reliable it is to let agents complete real purchases on a user's behalf. According to the report, nearly 50% of the tasks were executed incorrectly. Among the agents tested, Gemini and Muse scored the highest when it came to carrying out tasks like buying a TV. This is the earliest available record on the topic in the materials reviewed here; later developments will need to be added as further coverage appears.
AI-generated from 1 reports · updated 6 hours ago
- Heat index
- 80
- All sources
- 1
- All reports
- 1
- First seen
- 8 hours ago
Reports on this story headlines open the original
In what Fortune described as a first-of-its-kind experiment, AI agents including Gemini and Muse were asked to carry out shopping tasks such as buying a TV or laptop, and they failed nearly 50% of the time. Gemini and Muse scored highest among the agents tested, offering a concrete benchmark for how reliable agent-driven purchasing is today.
FortuneAI score 55
Other stories people are talking about
- Heat index 840OpenAI ships Images 2.6 with GIF and SVG output15 sources
- Heat index 675OpenAI says its cyber model pipeline confirmed 1,724 Linux kernel flaws and generated 948 privilege-escalation exploits11 sources
- Heat index 642RisingOpenAI GPT-5.6 Brings Major Agentic and Computer Use Upgrades13 sources
- Heat index 633RisingCat Wu, product lead for Claude Code, joins OpenAI9 sources
- Heat index 630NewSurgeOpenAI releases GPT-6 Cyber cybersecurity model7 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion