Show Notes
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 for The design details that make it far more polished than other personal agent launches How task lists, artifacts, and channels work as agent primitives Why a “proactive” agent that never nudges you is a growth problem How model latency kills your willingness to work with an agent synchronously Where it fell short on real tasks, from inbox triage to sales decks to launch videos Why 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].
More from How I AI
Brooke Lacey has been making videos since before Facebook had video, and she built a TikTok audience of more than 290,000 by learning to cut short-form videos herself. With over 25 years in tech, she now builds her own apps, including Zosha, a free mobile app for learning AI. In this episode, Brooke walks me through the Claude Code, FFmpeg, and Whisper workflow that edits her TikToks in about 15 seconds, how she mines her comments for new scripts, and how she runs a weekly short-form operation with no editor.
I put Meta’s new Muse Wonder (and Wonder Full) frontier models through the How I AI bench, which covers nearly 20 tasks across prototyping, agentic workflows, coding, writing, and creative work. I scored everything with an LLM-as-a-judge pass and my own voice notes, then pulled together the first-look results you see here.
Alex Cornell is a design director at Meta, where he leads design on Muse, Meta’s consumer AI agent. He came to the role with a long background in software product design, including time as a founder, and has spent the past year building one of the most thoughtful agent interfaces in the consumer AI space. Muse ships with a custom avatar, a three-layer status display, a personalized ideas surface, and a generative feed. Alex has been sharing the reasoning behind each of those design decisions publicly on Threads.
Kath Korevec is a member of the Product staff at OpenAI working on Codex, and she spent over a year building and using ChatGPT Sites internally before its public launch. She’s been on the front lines of shipping Plugin Insights, MCP plugin hosting, and the connector ecosystem, which now includes around 60 integrations.
John Lindquist created egghead.io, a developer education platform used by hundreds of thousands of working engineers. These days he’s building mega.dev, a hands-on program specifically for developers who want to do real work with AI agents, not just prototype them.