Weeks of testing AI agents Dot and Duet yield little beyond one helpful notification

A reviewer spent weeks testing OpenAI's Dot and Anthropic's Duet AI agents and found them not ready for prime time, identifying five upgrades that could make them more useful.

Read the full story at ZDNET AI ↗

Timeline · 1 report

2026-11-09 13:24 · ZDNET AI
I tested OpenAI Dot and Anthropic Duet for weeks – and all I got was one helpful notification

More stories

First How I AI personal-agent benchmark compares Grok Bot, Dot, Muse, and Claude Duet — How I AI
DeepSeek's Harness agent app reaches 1.54 million daily users — Bloomberg AI
Google Gemini Omni 1.2 Flash Is Live: 15-Second AI Video at 30% Lower Cost — DEV Community — AI
Analysis | Already using ChatGPT or Claude? These simple power-ups let you do a lot more. — Washington Post AI
OpenAI and Anthropic Valuations Fall as AI Market Rout Hits Fundraising — Bloomberg AI
The Week Ahead in AI: OpenAI Hires Hactron for Probe, Anthropic Details Claude 'Dreaming', Post-Election US AI Safety, Plus Upcoming Earnings & Events — AI Insider
The Small Business AI Tool Stack for Under $50/Month — DEV Community — AI
New study examines who pays for AI subscriptions in the UK's billion-pound AI boom — TechXplore AI & ML

Get the daily brief of stories like this at 6:30 every morning →