Two weeks with Claude Duet: the first personal agent that's a pro tool
danshipper · x · 2026-10-22
Dan Shipper publishes Every's two-week early-access review of Claude Duet, Anthropic's always-on personal agent launching in research preview, calling it the first personal agent he'd call a pro tool.
- Standalone app (iOS/Android/web) separate from Claude, running Opus 5.5; Pro/Max subscribers get priority access
- His usage shifted from mostly ChatGPT to roughly 50/50 with Claude
- Vs OpenAI's Dot: Duet is more proactive and doesn't drop tasks, with a Tasks tab showing ongoing work; Dot has faded since launch and recently failed to finish his taxes without alerting
- Duet currently has read-only computer access (write coming); email drafts weaker and sends sometimes blocked
- Feel: Duet is deeper and slower, a pro tool; Dot quicker and shallower
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