🎙️ How I AI: Grok vs. Dot vs. Muse vs. Duet + How Figma’s PMs actually use AI every day
- ID
- 42047
- Status
- summarized
- Published
- 03 Nov 2026, 12:02 AM
- Fetched
- 03 Nov 2026, 12:26 AM
- Provider
- Lenny's Newsletter
- Category
- product-startup
- Original URL
- https://www.lennysnewsletter.com/p/how-i-ai-grok-vs-dot-vs-muse-vs-duet
- Source URL
- https://www.lennysnewsletter.com/feed
Summary
- Score
- 6.5
- Created
- 03 Nov 2026, 12:27 AM
- Tags
- Audience
- ai_agent_usersvibe_codersdeveloperssaas_founders
What happened
The episode benchmarks four personal AI agents—Grok Bot, Dot, Meta's Muse, and Claude Duet—on nine real-world tasks including Slack replies, inbox triage, coding, Figma thumbnails, video editing, and shopping. Grok Bot scored 93% overall and won Figma, inbox triage, and shopping, while Muse was best for personal-life tasks and finished first on four of nine tasks; Claude Duet was consistently the slowest and asked for approval four times versus once for the others. The comparison is explicitly uneven because the agents lacked equivalent connectors and skills—Muse had no Slack or GitHub, blocking work tasks—and for serious coding the tester would still choose Claude or Codex rather than Duet's personal-agent interface.
Why it matters
Before standardizing on a personal agent, verify connector parity and interruption rate, not just benchmark scores: Muse's missing Slack/GitHub made work tasks impossible, and Claude Duet's four permission prompts versus one for the others changes whether it can be trusted for unattended workflows. For coding, treat personal-agent interfaces as secondary—Dot came closest to the intended Sentry fix and Duet found a second bug, but the recommendation is still Claude or Codex for serious coding.
Discussion angle
Run a small head-to-head with identical connectors and count human interruptions per task—then decide whether the agent's speed or its permission model is the real blocker for your workflow.