OpenAI dots early reviews: standout voice, rushed execution
OpenAI opened its personal agent product dots to early testers between late September and early October. First impressions split sharply: the voice plus tool/browser/computer-use combo is widely seen as best-in-class, while stability, authorization, multitasking, and transparency issues led multiple testers to call the product rushed.
Confirmed
- manosaie found ChatGPT voice mode still the best among competitors, and voice combined with tool calling opens a new paradigm of not having to actively manage the AI; he nonetheless felt the product seemed rushed given raised expectations.
- imjustnewatai reported dots failing to view even authorized logged-in sites.
- SeanOliver said dots took his Google login for a trip-planning task, then went unresponsive while silently reading his messages.
- KPGilmore liked the product but criticized the phone-call-style voice interaction versus one-click voice in Codex or ChatGPT Work.
- jdjohnson rated Dot smarter than Grok Bot and Muse, self-correcting after mistakes, but often ignoring user-set skills constraints.
- davis7 (relayed by RachelVT42) compared Dots with Grok Bot and called Grok Bot the only decent personal agent, citing Dots' single-threaded tasks, slow responses, and zero transparency.
Head-to-head
- Heavy user brandongalang (60+ hours weekly in agent harnesses) ranked Muse > Dots > Grok Bot > Instinct, noting it reflects his personal usage.
- Peter Yang argued dots and Muse don't directly compete: dots and Grok Bot target work tasks, while Muse and Instinct lean personal life.
Why it matters
dots marks OpenAI's formal entry into personal agents. Early word-of-mouth shows its voice-plus-tools combo leads, but engineering polish lags. Whether OpenAI closes those gaps in the launch window will shape the personal agent market.
2026-09-30 ~ 2026-10-02 · 12 related posts
Primary sources
- OpenAI dots first impressions: best-in-class voice, but the product feels rushed — manosaie ·
- Power User Ranks Personal Agents — Muse Over Dots and Grok Bot — After 60+ Hours a Week in Agent Harnesses — brandon_galang ·
- Hands-on with Dot: smarter than Grok Bot but keeps ignoring custom skill constraints — jdjohnson ·
- [source] Hands-on with Dot: smarter than Grok Bot but keeps ignoring custom skill constraints — jdjohnson · 2026-09-30
- OpenAI dots went silent after taking user's Google login, tester reports — SeanOliver · 2026-09-30
- [source] Power User Ranks Personal Agents — Muse Over Dots and Grok Bot — After 60+ Hours a Week in Agent Harnesses — brandon_galang · 2026-10-01
- Early user: OpenAI's rushed Dot can't even view the websites it signs into — imjustnewatai · 2026-10-01
- Peter Yang on OpenAI dots vs. Grok Bot and Muse: two separate races for personal agents — petergyang · 2026-10-01
- [source] OpenAI dots first impressions: best-in-class voice, but the product feels rushed — manosaie · 2026-10-02
- Early impressions: OpenAI dots feels rushed and underwhelming, but voice mode still leads — manosaie · 2026-10-02
- Early hands-on: OpenAI dot feels rushed but voice + tool use impresses — manosaie · 2026-10-02
- Agent tester: dots targets work, Muse targets personal life, they don't compete — AccBalanced · 2026-10-02
- Early OpenAI 'dot' user gripes: voice mode requiring a 'call' feels odd — KPGilmore · 2026-10-02
- Early users pan OpenAI's Dots agent: single thread, very slow, zero visibility vs Grok Bot — RachelVT42 · 2026-10-02
1 near-duplicate retellings: SeanOliver