Dots review: OpenAI's always-on agents read your Slack and flag conflicts first
every · x · 2026-09-30
OpenAI's Dot is a proactive, always-on agent with its own computer, working across 4,000+ apps via ChatGPT and connected plugins, quietly handling tasks 24/7 — from booking restaurants to acting like a high-agency chief of staff. Every's Dan Shipper tested it changing a flight and was impressed when it proactively read a Slack thread he'd missed to warn him of a scheduling conflict — though the experience oscillates between flashy and frustrating.
Related event: Hands-on with OpenAI's Always-On Agent Dot(4 posts)→
More from coding & agent
- LlamaIndex's Jerry Liu and Snorkel AI on why evals and RL environments remain unsolved — ajratner · 2026-09-30
- Nous Research partners with OpenAI to bring Sign in with ChatGPT to Hermes Agent — NousResearch · 2026-09-30
- Remote is now Codex again, and Codex Cloud works like any other host — Dimillian · 2026-09-30
- xAI bought dot.com and it redirects to the new Grok Bot launch page — whurley · 2026-09-30
- Using agent memory for root-cause analysis: recall similar incidents first, then verify — Majestic-Hat-5870 · 2026-09-30
- Matt Shumer on OpenAI's Dots: best-in-class AI, but UX isn't there yet — mattshumer_ · 2026-09-30