I tested 4 AI agents on 9 real tasks. Here’s who won.

I have personal-agent fatigue, so I ran the first How I AI personal-agent benchmark: Grok Bot, Dot, Muse, and Claude Duet across nine real tasks, from a Slack reply and a Sentry bug to a Figma thumbnail, inbox triage, a family newspaper, physics homework for a fourth grader, shoe shopping, and a ChatPRD launch video. I used computer use to operate them: Claude ran Dot, Codex ran the rest and scored the results live. Here’s the scoreboard—and which agent I’d actually trust for work vs. life. *Brought to you by:* WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more: https://workos.com?utm_source=lennys_howiai&utm_medium=podcast&utm_campaign=q22025 Firecrawl—Give your AI agents web data and beyond: https://firecrawl.dev/howiai *In this episode, we cover:* (00:00) Introduction (02:13) The personal-agent benchmark setup (05:00) The nine tasks and the prompts I used (07:20) Scoreboard overview (10:06) Task 1: Draft a Slack reply as me (11:39) Task 2: Cut a short-form video from raw Dropbox footage (14:56) Task 3: Fix a bug from Sentry (17:30) Task 4: Build a How I AI thumbnail in Figma (19:25) Task 5: Triage my inbox for to-dos (21:06) Task 6: Build a family newspaper (23:30) Task 7: Explain a physics homework question to a fourth grader (24:54) Task 8: Shop for shoes (26:46) Task 9: Make a ChatPRD Product Intelligence launch video (30:01) Final scores (32:38) My takeaways *Tools referenced:* • Grok Bot: https://x.ai/bot • Dot: https://chatgpt.com/features/dots/ • Meta Muse: https://ai.meta.com/muse/ • Claude Duet: https://claude.com/product/claude-duet • Codex: https://openai.com/codex • ElevenLabs: https://elevenlabs.io/ • Figma: https://www.figma.com/ • Sentry: https://sentry.io/ • Linear: https://linear.app/ • Dropbox: https://www.dropbox.com/ *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 *Have a really cool use case of how you use AI in your work? Let us know:* https://docs.google.com/forms/d/e/1FAIpQLSfP8wYCeDo5K0DxscDmoqgkxYY8ngA3B2anUDDvC4xadGTerg/viewform _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Claire Vohost

Oct 28, 202635mWatch on YouTube ↗

EPISODE INFO

Released: October 28, 2026
Duration: 35m
Channel: How I AI
Watch on YouTube: ▶ Open ↗

EPISODE DESCRIPTION

I have personal-agent fatigue, so I ran the first How I AI personal-agent benchmark: Grok Bot, Dot, Muse, and Claude Duet across nine real tasks, from a Slack reply and a Sentry bug to a Figma thumbnail, inbox triage, a family newspaper, physics homework for a fourth grader, shoe shopping, and a ChatPRD launch video. I used computer use to operate them: Claude ran Dot, Codex ran the rest and scored the results live. Here’s the scoreboard—and which agent I’d actually trust for work vs. life. *Brought to you by:* WorkOS—Make your app enterprise-ready, with SSO, SCIM, RBAC, and more: https://workos.com?utm_source=lennys_howiai&utm_medium=podcast&utm_campaign=q22025 Firecrawl—Give your AI agents web data and beyond: https://firecrawl.dev/howiai *In this episode, we cover:* (00:00) Introduction (02:13) The personal-agent benchmark setup (05:00) The nine tasks and the prompts I used (07:20) Scoreboard overview (10:06) Task 1: Draft a Slack reply as me (11:39) Task 2: Cut a short-form video from raw Dropbox footage (14:56) Task 3: Fix a bug from Sentry (17:30) Task 4: Build a How I AI thumbnail in Figma (19:25) Task 5: Triage my inbox for to-dos (21:06) Task 6: Build a family newspaper (23:30) Task 7: Explain a physics homework question to a fourth grader (24:54) Task 8: Shop for shoes (26:46) Task 9: Make a ChatPRD Product Intelligence launch video (30:01) Final scores (32:38) My takeaways *Tools referenced:*
Grok Bot: https://x.ai/bot
Dot: https://chatgpt.com/features/dots/
Meta Muse: https://ai.meta.com/muse/
Claude Duet: https://claude.com/product/claude-duet
Codex: https://openai.com/codex
ElevenLabs: https://elevenlabs.io/
Figma: https://www.figma.com/
Sentry: https://sentry.io/
Linear: https://linear.app/
Dropbox: https://www.dropbox.com/
*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 *Have a really cool use case of how you use AI in your work? Let us know:* https://docs.google.com/forms/d/e/1FAIpQLSfP8wYCeDo5K0DxscDmoqgkxYY8ngA3B2anUDDvC4xadGTerg/viewform _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

SPEAKERS

Claire Vo
host
Host of How I AI; AI practitioner and content creator focused on practical agent/workflow testing.

EPISODE SUMMARY

In this episode of How I AI, featuring Claire Vo and Claire Vo, I tested 4 AI agents on 9 real tasks. Here’s who won. explores claire benchmarks four personal AI agents across nine real tasks Claire Vo runs a nine-task “How I AI” personal-agent benchmark across Dot, Grok Bot, Muse, and Claude Duet using short, one-line prompts and an operator-agent workflow.

RELATED EPISODES