Skip to content

Claude Duet is beautiful. I still forgot to use it

How I AI

16m
Transcript

Original podcast

Summary

Written by a model from the transcript; not yet reviewed.

The host reviews Anthropic's new personal mobile agent, Claude Duet, examining its design polish, onboarding experience, and feature set compared to competing tools like OpenAI's Dots and Muse Meta. While praising the app's beautiful interface, intuitive onboarding, plugin inheritance, and Slack-inspired channel primitives, the host argues that the agent suffers from critical drawbacks including slow model latency, lack of proactivity, absence of a desktop app, and single-player limitations. Ultimately, despite its superior design polish, the agent fails to hold attention or drive re-engagement in a crowded ecosystem of AI tools.

  • Claude Duet inherits all existing plugins and connectors from your main Claude account during onboarding. 3:05
  • The agent creates first-class artifacts that can read existing files previously generated on your Claude account. 3:20
  • Sub-threads are organized into Slack-inspired channels to help compartmentalize different projects like sales. 4:04
  • Claude Duet currently lacks a desktop app companion, restricting the experience entirely to mobile. 5:49

Chapters

  1. 0:00
    Opening: Good and Bad News

    The host announces Anthropic’s new personal agent and expresses fatigue with new agents.

  2. 0:40
    Quick Walkthrough of Claude Duette

    Overview of the phone‑based agent’s features and design focus.

  3. 2:12
    Core Features: Plugins, Task Lists, Artifacts

    Discussion of Duette’s integration with Claude plugins, task tracking, and artifact handling.

  4. 4:04
    Channel Architecture and Collaboration

    Exploration of Duette’s channel system inspired by Slack for organized conversations.

  5. 5:27
    Proactivity Shortcomings

    The host critiques Duette’s lack of proactive nudges and notifications.

  6. 7:48
    Performance and Latency Issues

    Frustration with slow model responses and delayed task completion.

  7. 10:42
    Desktop App and Multi‑Device Experience

    Need for a desktop presence to keep agents in daily workflow.

  8. 14:06
    Multiplayer and Team Collaboration Gaps

    Limitations in sharing agents across teams and lack of true multiplayer features.

  9. 15:39
    Final Verdict and Call to Action

    Host summarizes strengths, areas for improvement, and invites listeners to try Duette.

Highlights

  • 1:08

    Target Audience for Claude Duetinsight

    Anthropic positions the agent specifically for small business owners, entrepreneurs, busy project managers, and CEOs rather than casual consumers or heavy software engineers.

  • 1:47

    Superior Visual Polish Over Dotsinsight

    The host notes that Claude Duet is exceptionally well-polished and beautiful compared to OpenAI's Dots, featuring zero sharp edges and a thoughtful onboarding flow.

  • 4:04

    Slack-Inspired Channel Organizationstrategy

    Anthropic borrows collaboration primitives from Slack by allowing users to break off sub-chats into specific channels like a sales project channel.

  • 5:27

    Lacking Proactivity and Notificationsinsight

    Despite being positioned as a proactive agent, Duet never pushed or bothered the user with notifications after the initial setup days.

  • 7:52

    Slow Performance Degrades Experienceinsight

    The host explains that Claude Duet is slow and suffers from high latency, which degrades the desire to work synchronously with the agent.

  • 10:25

    Missing Desktop App Integrationinsight

    The agent lacks a desktop app, forcing the user to stay on their phone during the workday instead of interacting via computer.

  • 14:01

    Single Player Limitationinsight

    Claude Duet is strictly a single-player product without multiplayer sharing features, making it difficult for small teams to collaborate.

Quotes

  • “I have good news and I have bad news. The good news is Anthropic just released a new personal agent and it's really well-designed.”
    Unnamed speaker · 0:00
  • “It is proactive, it can use all the tools and plugins that your Claude has access to.”
    Unnamed speaker · 0:51
  • “The agent itself has to be super proactive.”
    Unnamed speaker · 11:55
  • “I need you to be a little bit more annoying. I need you to be a little bit more proactive. I need you to be a little bit more noisy, or I'm truly going to forget you in the ecosystem of all my agents.”
    Unnamed speaker · 6:53
  • “The reality is like the latency and the inability to close loops meant that this particular agent product just really fell to the bottom of my use list.”
    Unnamed speaker · 10:06

About this episode

Anthropic's new personal agent, Claude Duet, lives on your phone, inherits all your Claude plugins and connectors, and is pitched at small business owners and busy professionals. It's the most polished agent launch I've seen: thoughtful onboarding, task lists, first-class artifacts, and Slack-style channels. But polish isn't enough when you're competing with every other personal agent for attention. I put it to work on my inbox and Slack, my sales pipeline, a Google Docs sales deck, a launch video, and finding Warriors tickets for my kids, and I'll walk you through what it nails, where it stalls, and what Anthropic needs to fix before it can become anyone's number one agent. What you’ll learn: What Claude Duet is and who Anthropic built it forThe design details that make it far more polished than other personal agent launchesHow task lists, artifacts, and channels work as agent primitivesWhy a “proactive” agent that never nudges you is a growth problemHow model latency kills your willingness to work with an agent synchronouslyWhere it fell short on real tasks, from inbox triage to sales decks to launch videosWhy missing desktop and multiplayer support keeps it out of my working stack— In this episode, we cover: (00:00) Personal agent fatigue: does Claude Duet make the cut? (00:40) What Claude Duet is and who it’s for (01:39) Why the design polish stands out (03:06) Task lists, artifacts, and channels (04:53) The icon (05:27) What I didn’t like: not proactive enough (07:02) Testing it on email, Slack, and Warriors tickets (07:41) Why latency matters so much in a personal agent (10:20) The missing desktop app (12:12) Sales pipeline and a Google Docs deck (13:10) Launch videos and the local skills gap (14:00) Single-player vs. multiplayer agents (15:05) Final verdict — Tools referenced: • Claude Duet (Anthropic): https://claude.com/resources/articles/claude-duet • Claude Duet Waitlist: https://claude.com/product/claude-duet • Claude Cowork: https://claude.com/product/cowork • Meta Muse: https://muse.ai/ • Codex (OpenAI): https://openai.com/codex • Grok Bot: https://x.ai/bot — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Transcript

0:00
16:21

3,051 words · 1 speaker

Topics

  • Muse
  • Anthropic
  • Slack
  • Codex
  • Claude Duette
  • Dots
  • Grokbot
  • Google
  • Google Docs
  • Figma

Page updated · transcript and summary are machine-generated