Sponsored

My Dot took care of demo week, image 1 of 1

Getting things done

My Dot took care of demo week

posted Sep 30, 2026

I worked on the dots live demo. Holly did a phenomenal job on stage today. If you've ever been there, you know the pressure is immense. She handled the recovery SO well. I flew to SF from Singapore for my 4th DevDay (and first an OAI employee). It's been a joy to get a small glimpse of what the dots team has been cooking. Truth be told, I was slightly skeptical of using dots when it was first introduced. I was already really comfortable using Codex and setting up plenty of automations. I wasn't sure how much more I'd get out of it. But a few personal examples that I can share publicly changed my mind. 1. En route to SF last week, my rideshare cancelled on me. There was the generic automated refund email. My dot immediately picked it up, knew I had a flight, and asked if I was okay. 2. During this trip, after days of DevDay prep, I woke up and told it, "Fuck my life, I'm so tired - what's on my cal today." It walked me through my day, then added one last thing: "Please take some time to eat and drink. Take one step at a time - you got it". Alone in a hotel room, that felt really reassuring. 3. On the building side, I've been using dot to spawn Codex threads that use CUA and ultrafast, and to proactively scan PRs for changes that might affect the demo. It's been useful for getting work done, and increasingly insightful and high-signal in ways I hadn't expected. I could delegate more confidently without repeating the same context for the umpteenth time. 4. Even this post came together with my dot, as I spoke to it throughout the day to investigate what happened and emotionally process it. Hope you give it a shot and see what I mean :)

First-hand from OpenAI employee Gabriel Chua (he worked on the Dots live demo): skeptical at first, his dot then (1) caught his cancelled rideshare's refund email, knew he had a flight, and checked on him; (2) walked him through his day when exhausted and added a caring note; (3) proactively spawned Codex threads and scanned PRs for changes affecting the demo; (4) helped investigate the day and co-write this post. Disclosure: author is an OpenAI employee posting personal first-hand use.

Getting things done

Dot 'Keet' finds the cheapest parking and grades a student's assignment

🚨🚨 OpenAI acaba de presentar los Dots en el DevDay y yo llevo usándolos desde el viernes: formé parte de las pruebas de la Dev Early Access Community. Te cuento cómo ha sido. Un Dot es un agente que está siempre encendido, con su propio ordenador en la nube. Lo conectas a tu correo, tu calendario y otras herramientas, y no espera a que le escribas: revisa por su cuenta qué puedes necesitar y te propone soluciones que muchas veces solo tienes que aceptar. La conversación se parece más a WhatsApp que a un chat con ChatGPT. Le pones nombre y avatar (el mío se llama Keet), y si le respondes con un 👍 entiende que aceptas y sigue. Lo que más me ha sorprendido estos días: 1️⃣ Este viernes tengo una formación y justo después un evento, con media hora entre medias. Lo vio por un email del evento, me avisó y me preguntó cómo pensaba ir. Le dije que en coche, me buscó el parking cercano más barato y me abrió la reserva con los datos rellenos. El pago lo hice yo. 2️⃣ Se puso a revisar la práctica que había entregado un alumno de AI Expert. Para ver el vídeo le pedí que instalara Whisper en su máquina, lo transcribió, revisó el repo con el conector de GitHub y me dejó una primera revisión. Ya no parto de cero. 3️⃣ Otro alumno había preguntado algo y Nino ya le había contestado. Lo vio y me propuso ajustar mi borrador para añadir solo lo que faltaba. Además se mete en Slack como un miembro más del equipo, y puedes llamarle por voz como si fuera una llamada de teléfono. Para esas tareas pequeñas que se acaban enquistando porque nunca encuentras el momento, me está resultando útil. ¿Lo vais a probar?

57.5K views on X

Dot reviews chat and email history unprompted: finds owed reply, double-booking, suspicious login

Dot reviews chat and email history unprompted: finds owed reply, double-booking, suspicious login

OpenAI lanza "dots" dentro de ChatGPT, agentes personales siempre activos y proactivos para ayudarte. Vengo usándolo hace unos días como parte de un programa de OpenAI; la diferencia con el chat normal es que la conversación es como si fuera WhatsApp y te manda mensajes el dot cuando necesita confirmar algo con vos. Los dots tienen una computadora con Linux para usar en la nube que también vos podés usar desde la app de ChatGPT para instalar apps o loguearte en sitios. En mis primeros minutos me dio impresión. Inmediatamente tomó mi historial con ChatGPT y mi mail y sin mediar ningún mensaje ni pedido, empezó a decirme cosas revisando historial e hilos de conversación. Me encontró la solución a un bug de un cliente que todavía tenía que contestarle. Me mandó cosas como "ojo que le dijiste a X que podías a las 3 el viernes pero a las 3 le habías dicho a Y que ibas a dar el curso". En un momento me dijo "disculpá, pero para chequear, ¿fuiste vos que entraste a tu gmail desde otro dispositivo?" controlando la seguridad de mi cuenta porque le pareció "sospechoso". También se pasó a veces, sobrecomplicando las situaciones. Se lo dije, veremos si lo aprendió. Dots funciona dentro de la app mobile y la app de desktop. A cada dot le ponés un nombre y un avatar.

Maximiliano Firtman

21.7K views on X

Getting things done

Dot 'Boo' triages Slack and email, catches a flight/meeting conflict

BREAKING: @OpenAI just announced Dots—always-on agents in ChatGPT I've been testing it for the last few days @every, here's a quick vibe check: What you should know: - They'll look familiar if you've used OpenClaw, Muse, Instinct, or Grok Bots. - Your Dot sits in the redesigned ChatGPT sidebar right below the “New chat” button - It has its own cloud computer that lets it work while your laptop is closed. You can text it any time or call it on the phone. Vibe check—the good When it’s working, it changes the way I use ChatGPT: I interact with Boo (my Dot’s name), and Boo orchestrates ChatGPT threads, reads my email, uses Slack, and more. It automatically filters incoming Slack requests and emails so I can quickly triage items without opening my inbox. When I was rescheduling a flight, Boo warned me that my new flight time would conflict with a meeting request from Slack that I hadn’t read. That’s the promise: an ongoing agent that filters what needs my attention and acts proactively on my behalf, in one long-running chat thread. Vibe check—the bad But the version I tested over the last few days was buggy and lacked some features I would expect, like iMessage support. I had frequent issues with permissions and dropped messages, and my Dot was unable to connect to its own in-app browser. The verdict During testing, I found myself reaching for my Dot over starting new Codex threads, so it has definitely become a habit despite the frustration. And during the tesitng period the team was rapidly fixing issues—so I'd expect most of this to be smoothed out over the coming days and weeks. Unless you love new things with rough edges, I’d recommend waiting a week or two to try it. OpenAI will have solved a lot of these paper cuts by then. If you’re already deep into Grok Bots, Muse, or Instinct, it’s probably not an immediate switch unless you’re also a big ChatGPT or Codex user. Read the live feed on @every: https://every.to/live/openai-devday-2026

18.1K views on X

Getting things done

Three power-user hacks: all-day Dot phone calls, shared-doc agent coordination, reusable skills

OpenAI launched dots today. I’ve been using them personally and professionally for weeks. My top 3 hacks to get the most out of your dot: 1. Stay on a phone call all day with your dot. Chat while you work and let your dot keep you updated on what’s happening around you and your team 2. Give your dot and your other agents, like Instinct, access to a shared Google Doc and tell them to coordinate using it 3. Have it create and improve skills for your recurring work, then set up automations to use them. Share those skills with your coworkers and be the office hero

39 views on X

Pires tests his Dot "Gepêto" via live phone call, already helping his agency's work

Pires tests his Dot "Gepêto" via live phone call, already helping his agency's work

Trump resolveu chamar a IA de superinteligência no governo americano… aí fui perguntar pro meu agente de IA o que ele achava disso! Esse é o Gepêto, meu Dot, o assistente pessoal da OpenAI que tô testando. A gente conversa por mensagem e ligação, e ele me ajuda a organizar tarefas, pesquisar, preparar arquivos e executar ações nos apps conectados. Já tá ajudando nas demandas da Bright. #dots #openai #chatgptbrasil

Dot answered a waiting Claude Code session over a phone call

Dot answered a waiting Claude Code session over a phone call

Comment DOT and I'll DM you the guide. Follow first so the DM can reach you. OpenAI's dots take "phone calls" so I called mine and asked it about a Claude Code session that was chillen waiting on me. It used its OWN computer (Linux), logged into my /RC enabled claude code sessions via browser, told me what the session was waiting on, and typed my answer in for me. (Silly use case but real ones exist) What would you use this for? #openai #claudecode #aiagents