More projects built with Dots
Continue exploring projects, experiments, and ideas from the Dots community.
Dot runs parallel Codex jobs and reports status like a team lead
Dots 써보니까 느낌이 좀 이상하다. 예전엔 내가 AI한테 “이거 해줘” 하고 기다렸다면, 지금은 내가 대장이 된 느낌임. “이거 수정해.” “저건 Codex로 돌려.” “이미지도 하나 만들어.” “지금 어디까지 했어?” 하면 바로 대답해준다. Codex 작업도 여러 개 병렬로 던져놓고 Dots한테 전체 상황을 물어보면 된다. 게다가 클라우드에서 돌아가니까 컴퓨터를 꺼놔도 작업을 이어갈 수 있다. 이미지 생성도 시키고, 필요한 정보도 바로 물어보고, 답변 자체도 상당히 빠르다. 그리고 제일 마음에 드는 부분. Dots랑 일반적으로 대화하는 건 ChatGPT 사용량에 포함되지 않는다.Her Dot Jordan built the site and 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.
I Gave ChatGPT Dots a Real Job — Here's What Happened
I gave ChatGPT Dots, OpenAI’s new always-on AI agent, a real job: handling the customer workflow for a painting business — quotes, owner emails, customer replies and bookings. Not a demo. Here’s what happened. OpenAI introduced Dots in September 2026. Dots are powered by GPT-6 Astra, have their own cloud computer and browser, and can keep working on tasks in the background. I wanted to go beyond the polished demos and see what happens when Dots has to handle actual business work from start to finish. In this video: → Setting up ChatGPT Dots for a real painting-business workflow → Testing the quote calculator — did it get the numbers right? → Drafting owner emails and customer replies with approval → Handling a booking end to end → Why some browser based tasks took 2+ minutes → My verdict: is ChatGPT Dots ready for real business work? ⏱️ CHAPTERS 0:00 Giving Dots a Real Job 0:55 Setting Up the Painting Business 3:23 Building the Painting Workflow 6:54 Test 1: Calling the Dots AI Agent 9:08 Test 2: Reviewing the Website Dots Built 10:23 Test 3: Testing Customer Enquiries 11:59 Test 4: Getting Live Project Updates 13:00 Test 5: Email + Calendar Booking Live 17:24 Final Verdict: Is Dots Ready for Real Work? 🤖 Want an AI agent like this built for your business? WebCrunch Systems builds AI automations for small businesses. For AI automation projects, collaborations, or business enquiries: gurmeetbuildsai@gmail.com 📌 Watch next: AI receptionist video 👋 I’m Gurmeet, a former Shopify senior software engineer with 18+ years of experience building software. On Gurmeet Builds AI, I test AI tools on real workflows — not just demos. 🔔 Subscribe for practical AI-agent builds, tests and real-world experiments. #ChatGPTDots #OpenAI #AIAgentsDot organized my brain-dump notes and drafted messages
Brain dump Today / This Week / Waiting. My ChatGPT Dot organized my notes and drafted messages for review. Real chat excerpts, personal details cropped; nothing sent or cancelled. Would this help your week? https://youtu.be/54uvCSI3Wvk #a2zai #ChatGPT
My OpenAI Dot Works Outside My Projects — That's the Problem
My AI assistant can do useful work. That doesn't solve the problem of working outside the projects where I keep the background and rules. Brian describes two jobs he gave his Dot Ava: adapting his exercise-routine application and looking for a better animation tool for his story. Both ended up in separate chats outside the existing projects, where he wanted the accumulated context and instructions applied.Dot negotiated a denied refund back open and caught a missed promise from a 2h20 class
Uma semana com o Dot e duas situações me chamaram a atenção. Na primeira, ele leu a transcrição de uma aula de 2h20 que dei no fim de semana. Encontrou uma promessa que eu tinha feito no meio dela, conferiu agenda e e-mails e veio perguntar pelo horário e link da próxima aula. Eu não tinha pedido essa revisão. Na segunda, conduziu um pedido de reembolso que a empresa havia negado. Pesquisou uma base para pedir reconsideração, preparou a réplica e negociou. Eu só fui aceitando o que ele sugeria, sem nem abrir meu e-mail. A empresa aceitou abrir uma exceção; o print mostra esse aceite e minha autorização para seguir. Naquele momento, ainda faltava processar o estorno. O que me interessa é ele voltar ao meu contexto, encontrar uma pendência e me trazer uma ação sem esperar que eu formule mais um pedido. Alguns agentes pessoais chamam essa revisão periódica de heartbeat. O Dot usa GPT-6 Astra. Minha impressão é que esse modelo pesa bastante na capacidade dele. Nos planos pessoais, ele começa no Pro de US$ 100/mês, com liberação gradual. Também há acesso no Business Premium e em beta no Enterprise. É promissor. Ainda está longe de ser indispensável para mim como um celular. Mas, entre os agentes pessoais que experimentei, está entre as melhores experiências de proatividade que tive. Compartilha o que o Dot fez por aí? Fontes sobre o produto e os planos: https://help.openai.com/en/articles/20001530-getting-started-with-your-dot https://help.openai.com/en/articles/9793128-about-chatgpt-pro-tiersMy Dot is a 'super-excellent secretary': daily decision briefs and meeting prep
ChatGPTの「Dots」、使える人はすぐ試した方がいいです!かなり便利です😊 一言で言うと、 「超優秀な秘書 兼 社長室長」 最初は正直、 「今までのChatGPTと何が違うの?」 と思っていました。 僕は以前からChatGPTに、Gmail、Google Calendar、Slack、Drive、Notion、などを接続して使っていたので、できることだけを見ると、そこまで新しく感じなかった。 でも、少し使ってみて違いが分かってきました。 Dotsの面白さは、 「AIにツールを使わせる」 ではなく、 「AIに仕事を担当させる」 ことにある。 例えば、 毎朝、メール、Slack、カレンダーを確認して、「今日、自分が判断すべきこと」を5つだけまとめてもらう。 自分が「返信します」と言ったのに返していないもの。相手から返信待ちのもの。数日止まっている案件。これらを継続的に管理してもらう。 会議の前には、過去メール、前回の議事録、関連資料を確認して、「今日聞くべきこと」「前回から残っている宿題」をまとめてもらう。Dot "Boo" posts model-testing results to Slack and brings back replies over the weekend
OpenAI's Dots launched last week and they've taken over @every. A few things that stand out: They protect your attention. Over the weekend, my Dot posted my model-testing results to Slack and brought back replies. I could keep working without opening Slack and disappearing down a rabbit hole. My weekend stayed pretty clear and calm. They're useful for the little things you miss. People at Every are using them to pull important information out of school emails, catch missed Slack messages, and flag account-access requests. Voice makes them useful away from your laptop. Our head of video was talking his Dot through video edits while running around getting our launch out. The ecosystem matters. Dots feel roughly at feature parity with Muse, Instinct, and Grok bots. But having an agent connected to the ecosystem you already use for work and life is a real advantage. If you use ChatGPT, I recommend trying one. Permissions are still frustrating. I have to approve the same basic thing multiple times, and sometimes even after I approve it, my Dot says it can't do it. That needs to get fixed. I'm less convinced we'll stay loyal to the characters. Mine is named Boo, and I'm attached to him. But I felt that way about my OpenClaw agent, too. When something better comes along, I switch. In a year, I expect to be using a persistent agent. Boo will probably be dead. RIP, Boo. I get into all of this at the start of this week's podcast, and then sit down with @bigwilliestyle to talk about where we go from here. In a lot of ways, Dots and GrokBots remind me of a wave we went through with OpenClaw eight months ago. We talk about personal vs. company agents, why we built our own company agent, and whether companies will end up with a whole shadow org chart of agents. Full episode below.
What I learned after 1 week with ChatGPT Dots: what to delegate to the 'AI secretary' — and what disappointed
One week testing ChatGPT Dots in work and daily life. Real moments it helped: handling a flight change, train timing checks, proactive suggestions from email/calendar, ongoing news notifications, and a voice consultation with my wife. Also: what disappointed, his delegation boundaries/custom rules, and how he set up the Dots computer.
I finished my sales-meeting prep in 3 minutes just by calling ChatGPT (Dots demo)
10 minutes before a sales meeting I phone-called my Dot and asked 'what should I propose today?' In about 3 minutes it organized: what I should propose, the president's vs the division manager's interests, what to confirm in the meeting, and small-talk topics. The real call with the Dot is published nearly as-is (only hesitations edited).Stress-tested an OpenAI Dot on a hiring task — and tried to trip it up
I Gave an OpenAI Dot a Hiring Task, Then Tried to Trip It Up I handed an OpenAI dot a hiring task, changed the rules, and added a duplicate. Save this for a grounded look at OpenAI's new agents. Dots are OpenAI's always-on agents. Each has its own cloud computer and can coordinate work through ChatGPT Work or Codex. The test (all fictional): 4 application summaries, a role brief, and clear boundaries: organize evidence, keep gaps visible, leave decisions to the human. The catch it caught: applicant two claims Python, but the project was a browser interface with no Python sample. The dot kept both facts visible and marked the evidence unknown, without treating a claim as proof. Changed priority to project-first: it reordered the columns but changed nobody's eligibility. Added 2 more plus a duplicate: result was 6 unique applicants, not 7. Evidence stayed attached correctly. Asked for an interview draft for applicant one: 5 project-specific questions, invitation left as a draft with placeholders. We chose the applicant, not the dot. The honest part: one staged session, fictional data, no comparison to regular chat. It organized. The decisions stay human.Dot surfaced a forgotten payment, then worked out how to route it through credits
코덱스에서 dot 이란 녀석을 발견한지 몇주. 일은 많고 귀찮아서 안보고 있었는데. 유튭에 이걸 활용하는 인터뷰 얘기에 궁금해서 연동해봄. 연동하자마자 잊고있던 결제건을 들고 달려옴. 내가 알기론 크레딧 지원받은돈 있는데 거기서 차감되는게 아니고 돈을 내야 하는거지? 물으니 지혼자 이것저것 알아보더니 개발로 해당 크레딧 연동하는 방법을 알려줌. 그렇게 개발건이 늘었다. [EN: I'd noticed the 'dot' inside Codex weeks ago but was too busy to look; a YouTube interview about using it made me curious, so I connected it. Right after connecting, it came running to me with a payment charge I'd completely forgotten. I asked, 'I thought I had supported credits — isn't it deducted from there instead of paying?' It investigated on its own and told me how to link those credits through development. Which is how my development workload grew.]
ChatGPT Dots Built This Website — My Honest Verdict
Can ChatGPT Dots build a website? I put my Dot, nicknamed Bub, to work on a water-restoration site and followed the build from setup to the finished desktop and phone-sized layouts. This hands-on build shows the requests, website improvements, polish, 21st.dev designs, an experiment with liquid-glass buttons that I rolled back, and the changes I still had to guide. Bub used the Higgsfield connector for the hero video. My takeaway: GPT-6.1 Sol High for the video build, Bub for the website build — with me checking the work along the way.
I'm Overwhelmed. Can ChatGPT's New Assistant Help?
The AI Essentials (YouTube) put his own Dot, named Scout, through three real tests: organizing his day, brainstorming thumbnail ideas and turning one into a SketchUp 3D model, and building a save-for-later website for videos and articles. Shows the actual results, the bugs he ran into (conversation and file-link errors, image-transfer problems), and whether Dots can really take work off his plate. First-hand test results.
I Gave ChatGPT Dots 10 Tasks in One Phone Call
AI with Amit (YouTube) spent the week after DevDay throwing real work at his Dot, named Morpheus: then jumped on a live voice call and stacked 10 tasks into one conversation - flights, NFL tickets, hotels, late-night food, and calendar reminders, all running in parallel. Earlier that week his Dot sliced 3D print files, mined YouTube comments for content ideas, and an inbox check caught a subscription about to charge him. First-hand demo with real results.My Dot planned my entire 2-day Fukuoka + Kumamoto trip itinerary
비서가 있어도 이 정도는 못 한다. 후쿠오카+구마모토 2일 일정을 GPT DOT x aside 조합에 맡겨봤다. 이동 동선, 가볼 곳, 평점 4.2 이상 맛집, 가성비 숙소, 구글맵 카테고리 정리까지. 요청 몇 줄에 반나절 일이 끝났다. 여행은 예시일 뿐이다. 같은 구조면 출장 일정, 자료 조사, 홍보물, 보고서도 '시키면 끝나는 일'이 된다. 10월 말 진주바이오센터 강의. 올해만 벌써 세 번째 앵콜이다. 이번엔 DOT x aside로 마케팅·업무 자동화를 직접 구축한다. 이미지·영상 생성은 기본, AX 최적화와 바이브코딩까지. 올해 70번 넘게 강의하며 확신한 건 하나. AI는 어렵다. 그래도 써야 한다. 결국 효율로 말하게 되니까. 기관·기업 교육 담당자라면 DM 줘. 조직 업무에 맞춰 설계해줄게.
First-hand verdict: is ChatGPT Dots worth $100/month? 3 ways I actually use mine
Is ChatGPT dots Worth $100 a Month? The Good, the Meh, and 3 Ways I Use It — Japanese creator Keisuke Takasawa's first-hand field report after trying Dots: a look at the Dots screen, what he finds good vs underwhelming, and how he actually uses his Dot day to day.
Dot runs a daily briefing, scheduled learning from saved links, and transcript-to-draft pipeline
OpenAI Dots: 3 Jobs to Give Your Agent on Day One — first-hand walkthrough of three practical jobs the creator gives their Dot: a daily priorities briefing, turning saved links into scheduled learning, and turning a video transcript into content drafts. Shows the workflows running live across Notion, Gmail, Google Calendar and Google Drive, including custom approval rules.
OpenAI dots built my office in 3D (Blender)
OpenAIの「dots」(2026年9月29日発表)を、実際に使った例と公式情報で整理。うちのdotに頼んだら、酒田の拠点「未来創造館」を写真と公開案内図からBlenderで3Dにしてくれました(寸法は推定・内装はイメージです)。料金・日本で使えるか・利用枠も整理。 #OpenAI #dots — Creator's Dot turned photos + publicly released floor plans of their Sakata office 'Mirai Souzou-kan' into a 3D Blender model.
I Asked My ChatGPT Dot to Plan a Tokyo Sightseeing Trip
ChatGPTのdotに、東京観光の行き先を相談してみました。観光に使える時間や人数などを伝えて、候補を提案してもらうまでのやりとりを紹介します。今回伝えた条件は、出発地は東京駅、大人1人、移動時間を除いて観光に使える時間は4時間。相談すると、誰と行くのかを確認され、条件を伝えた後に次の候補が返ってきました: 浅草、上野、丸の内・皇居東御苑。その後、行く日や午前・午後のどちらを予定しているかも聞かれました。記録日: 2026年10月4日、動画はそのとき私のアカウントで行った相談の記録です。Projects








