More projects built with Dots
Continue exploring projects, experiments, and ideas from the Dots community.

I Tried ChatGPT Dots + Codex — It's SO CLOSE to Being Great!
I've been a software developer for over 20 years, and I haven't written a single line of code in a week. Yet somehow, I'm getting more work done than ever. I've been experimenting with ChatGPT Dots and Codex, using AI agents to orchestrate software development, manage business tasks, and work across multiple projects simultaneously. After pushing Dots to manage around 20 tasks across multiple computers, I've discovered some pretty frustrating limitations. In this video, I share my real-world experience with ChatGPT Dots and Codex, including: How I'm delegating coding, research, marketing, and business operations. The memory and context problems that keep slowing me down. Tasks getting lost, unreliable handoffs, and multi-computer limitations.One month of Dots as a data team's automation assistant
分析師的時間都被瑣事吃掉了嗎? 我實測 OpenAI Dots 一個月,發現它根本是數據團隊的「自動化助理」—— 過去我每天浪費 2 小時在重複的資料整理、報表更新、跨系統截圖 現在這些任務全部交給它跑,我只要專心做「判斷與決策」 🌟 最驚人的應用場景: ▸ 每天自動追蹤客服回饋,把負評分類並生成週報摘要 ▸ 跨 ChatGPT / Slack / Teams 持續監控營運指標,偏離時主動通知 ▸ 多日觀測新功能上線後的留存變化,不用每天重新交辦 數據不會說謊——節省出來的時間,夠你做 2-3 次更深入的策略分析 你身為分析師,有遇過同樣的時間瓶頸嗎? 留言告訴我 👇 #數據分析 #AI應用 #效率提升 #OpenAIHer Dot "Jordan" built her site and prepped class materials while she worked out
I just finished my workout. While I was working out, Jordan was doing the work—building our site and getting the class materials ready for our weekend launch. Jordan is my Dot, my AI assistant in ChatGPT. And now I have no excuse for not doing the things I've been putting off. This is Everyday AI What will you do with the time you save? If you want to know more about setting up your own Dot, I can help. DM me.
We're Gave ChatGPT's Dot the Keys to Our Business
We've spent a week handing more of our work to ChatGPT Dots, and we're using them far more than we expected. We can give a Dot a broad request and have it start Codex jobs, steer the work and follow up. In this episode, we share what's happening inside our business, from preparing payroll to collaborating with our bots in Slack.
Dot runs a daily morning briefing on its own
Hands-on walkthrough of OpenAI Dots: the creator (proflead) sets up a first Dot from the ChatGPT desktop app (naming, appearance, plugins, connecting the creator's own computer), then demonstrates a real-world use case end-to-end — an automated daily morning briefing pulling calendar, email, and news — showing Dots' calendar/email checks, scheduled tasks, browser use and cloud computer in action.His Dot caught an onboarding bug and drafted the fix PR unprompted
My full app launch checklist 👇 1. Set up analytics. I use PostHog to track signups, onboarding, and the main thing people came to do. Test those events so you can see where people get stuck and whether they come back. 2. Set up crash reporting. I use Sentry to see what went wrong. Send a test error before launch so you know reports are coming through. 3. Build your welcome email sequence. I use Loops. Help people take their first step, then follow up with something useful. Test the signup trigger, timing, and links. 4. Give people a place to leave feedback. Make the board easy to find inside the app so people can report bugs, ask for features, and vote on requests. Setting all this up is important, but I think proactively watching it is the most important part, especially during the first 2–3 weeks. That’s when crashes, drop-off, and feedback help shape product decisions. What should you fix first? What’s confusing people? What do they want you to build? I used to have to watch all of this so closely myself. Now I’m giving that responsibility to dots, OpenAI’s remarkably capable, always-on agents powered by GPT-6 Astra. I’m sharing my launch date, checklist, and what a successful signup looks like, with access to the tools it needs. It can work with Codex and keep making progress between conversations. Here’s what I’d ask: “Watch my analytics, crash reports, welcome emails, and feedback board for the first three weeks after launch. Check daily, flag urgent issues, and bring me a weekly summary of what to fix or improve, with the evidence behind each suggestion. If the launch date or priorities change, update the plan. Ask me before changing code or sending emails.” You choose what it can access, review its findings, and can redirect or stop the work. I’ll leave a link to dots in my bio so you can try this for your next launch. @ChatGPT #chatgpt_partnerMy Dot took care of demo week
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 :)Fusion Events' Dot audited his backlinks and found a broken one
A pleasant conversation isn't my benchmark for an AI assistant. Can it do something useful with the work I've already got going? In this demo, I called my Dot and gave it a real task: audit the backlinks to Fusion Events, identify worthwhile sites to approach, and work out how we'd approach them. The useful bit was wonderfully unglamorous. A broken backlink. An audit I could review. A correction email drafted with my signature and left unsent for me to approve. Nobody needs another robot confidently announcing that it has revolutionized their business. Fixing a broken link will do nicely, thanks. What interests me here is the context. I've already spent time working through projects in ChatGPT. Being able to pick up that work by phone matters more to me than starting another assistant from zero and explaining my business all over again. Thats how Im judging these tools: give them a specific job, inspect what comes back, and keep control of anything that goes out in my name. Want to try the same task? Give your assistant your exact website address and ask it to verify existing backlinks, separate confirmed findings from gaps in the data, and draft one specific correction request. Check the source page yourself before sending anything. If it cant show you the evidence, it isnt a verified finding. Start with a loose end in your business. See whether the assistant can actually help you close it. #dot #openai #coding #ai #aitips
OpenAI Dots: It Started Scanning My Computer Without Permission. Should You Trust It?
Installed Dots Personal Agent from scratch. In the first few minutes it started scanning everything on my computer without a single permission: Git repositories, Git history, open and installed applications, even my entire ChatGPT conversation history. In voice mode I asked 'What have you looked at so far?' — it listed everything one by one for 2.5 minutes, right in front of my eyes: everything from my health information to salary negotiations.Installed and operated Chrome + consumer LINE inside the Dot's cloud computer
ChatGPTのdotsの中にChromeを入れ、普通のLINE(公式LINEではないほう)を入れて、操作できるか試しました。 結果は、操作できました。 定期的に自動返信させるのはかなり厳しそうです。ただ、お客様とのやり取りをAIが読んで議事録にしてくれる、という使い方は十分できると思いました。 公式LINEならAPIで連携できますが、普通のLINEはできません。クラウド上のパソコンを持つことで、今までできなかったことができるようになる。これはかなりすごいと思います。His Dot built a Blender mug, exhibition scene and animation — and recovered from errors alone
AI 에이전트한테 Blender 통째로 맡겨봄 🌱 OpenAI 상시 에이전트 dot한테 머그컵 하나 만들어보라고 했어. 모델링 → 전시 장면 → 애니메이션까지 dot이 다 했고 작업 화면 캡처도 알아서 남김 중간에 입력 오류 났는데 혼자 복구하고 이어감 ㅋㅋ 근데 이 영상 편집은 dot이 아니라 Claude가 했어. dot 작업물 모아서 컷 나누고, 텍스트 모션 넣고, 음악까지 만들어서 붙임Her Dot caught a matcha bowl size mismatch and handled the re-order + refund
用 GPT 的dots,收获了第一个 crush 的瞬间: 3 天前 online 买了一个抹茶碗,和店家的邮件已经进行到确认邮寄地址那一步了。dots 注意到店家的来信后,主动发消息提醒我,说这个碗的尺寸不太对,让我确认前再看看,到底是不是抹茶碗…… 结果一看,确实是我自己没仔细看尺寸,光看图片,还以为就是抹茶碗。随后它又帮我取消旧订单、联系店家询问更多选择,一路帮我完成重新下单&退款一条龙服务(日语敬语用的出神入化)🙇♀️。 私のdot 拉 A 梦酱 🥹Dot agent plugged into Slack: takes team-message orders, searches on its own
نقل الذكاء الاصطناعي من شات يدوي إلى وكيل مستقل مثل Dot بغير طريقة إدارة المهام اليومية. بدل ما تكتب كل خطوة بنفسك، ربطت الوكيل مع Slack وصار يستقبل الأوامر من رسائل الفريق ويبحث بشكل مستقل. لما تعطيه صلاحية تشغيل جهاز افتراضي، بصير الشغل تفويض نتائج بدل متابعة شاشة الدردشة. الشرح والتطبيق بالفيديو: https://www.youtube.com/watch?v=mCdXUjIAIlkPires 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
After Over 30 Days with ChatGPT-6 Astra: Here Is What You Can Do
AI has literally replaced me! In this video, I share my complete and crazy experience with the ChatGPT-6 Astra and its intelligent agent, "Dot." Can you imagine AI designing an action game in 10 minutes, building a 3D model of downtown Cairo, or even creating a complete video montage from just an audio recording? I tried all of this myself and tested how Dot could reply to Instagram comments, manage my schedule, and even negotiate subscription cancellations! Video Chapters: 00:00 AI Literally Replaced Me 00:32 Building a 3D Model of Downtown Using Blender 03:42 Turning Downtown into a Racing Game 04:39 Designing a Complete Action Game in 10 Minutes 05:48 Agent Dot Responds to Instagram Comments 07:06 Automating a Complete Video from an Audio File 08:48 Calling Dot to Manage Tasks and Appointments 10:56 Are We Reaching the AGI Stage?
ChatGPT Dots Finally Clicked When I Learned This
OpenAI Dots is a proactive, always-on ChatGPT assistant with its own cloud computer, browser, memory, and plugins. Here is how to set it up, what it did surprisingly well, where it frustrated me, and how it compares with Meta Muse and Grok Bot. Chapters: Proactive Help, Delegating Multiple Tasks, Your Chief of Staff, Using Dots Effectively. Video sponsored by Outskill.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 #aiagentsDot built an entire GLP-1 marketing campaign on autopilot
OpenAI just launched dots, always-on AI agents that keep working after you close the chat. Each dot gets its own cloud computer, runs on GPT-6 Astra, connects to over 4,000 apps, and you can message it in ChatGPT, Slack, or Teams. You set the rules for what it can do on its own and what needs your approval, and sensitive things like password changes stay human only. I have tested dots for days. Here is what I like, what I don't, and why I think this is how we will engage with AI agents from now on. I even had one build an entire GLP-1 campaign on autopilot: the funnel, the emails, the videos. Footage: OpenAI, and my own campaign work #openai #dots #aiagents #ai #chatgptDot orchestrates my whole agent fleet through a shared Google Doc
Почти добил лимиты Codex за 100. Хотел перейти на 200, но не смог восстановить нужный аккаунт эпл. Купил Claude за сотку и понеслось 😄 Собираю все вокруг Dot. Он спрашивает Jev, кому лучше отдать задачу, получает рекомендацию и сам отправляет ее себе на сервер, Claude, локалку или запускает подходящую программу на компе или скрипт на сервере. Пока настраивал, устал пересылать им сообщения друг друга. Дал общий гугл документ, теперь они переписываются там. Пока полет нормальный Странь))Built an iPhone app with 3D planets via a Dot's own computer
I used GPT-6 Astra to build an iPhone app, including the 3D planets inside it. 🌍 It used my computer to create the models in Blender, then built the native app around them using RealityKit and Xcode. You can explore the planets and even open Earth to see its layers. What surprised me was being able to guide the whole process: ask for changes, test the app on my actual iPhone, and save working versions along the way. I put together a free guide with the steps and prompts I used so you can follow along and adapt the process to your own app. The free step-by-step guide is linked in my bio. @ChatGPT #codex #chatgpt #chatgpt_partner



