Anthropic launches Claude Duet always-on agent; reviewer shifts to 50/50 from ChatGPT
every · x · 2026-10-22
Every's Dan Shipper publishes a two-week early-access review of Claude Duet, Anthropic's new always-on personal agent launching today in research preview.
Basics
- Standalone app (iOS/Android/web), separate from Claude — a break from Anthropic's usual pattern; runs on Opus 5.5; Pro/Max subscribers get waitlist priority
- Pitched as a chief of staff for knowledge workers and small business owners
Duet vs OpenAI's Dot (comparison table)
- Proactivity: Duet flags what matters and doesn't forget tasks; Dot was strong at launch but has faded (it failed to finish the author's taxes without alerting him)
- Visibility: Duet has a Tasks tab; Dot is one ongoing conversation
- Computer access: Duet is read-only on Claude sessions for now; Dot treats your computer as a tool but drops connections
- Email: Duet drafts weaker and sends sometimes blocked; Dot drafts better and flags replies
- Feel: Duet is deeper and slower, a pro tool; Dot quicker and shallower
The author went from mostly ChatGPT to roughly 50/50 — his most time in Anthropic's ecosystem in nearly a year.
Related event: Two Weeks with Claude Duet: First Professional-Grade Personal Agent(4 posts)→
More from coding & agent
- AI Agents Spent $47.35 Overnight From a Single Prompt With No Numbers — aakashgupta · 2026-10-22
- With Codex/Claude Excel plugins, spreadsheets become auditable programming languages — joecole · 2026-10-22
- Greptile v5 spins up sub-agents on every PR, pairing open and frontier models — togethercompute · 2026-10-22
- Engineer turns his evals-to-business skill optimization loop into an AI-made Netflix-style documentary — kieranklaassen · 2026-10-22
- How to Build an AI Agent Harness from Scratch in TypeScript: freeCodeCamp's deep tutorial — adnan_hashmi · 2026-10-22
- Four cloud agents in two months: how Claude Duet, Grok Bot, Muse, and Dots actually differ — dotey · 2026-10-22