Gave his Dot a real job
added
OpenAI Just Launched Dots. Here's The Truth About It. Get my exact OpenAI Dots setup, safety rules, and copy-paste prompts here: https://sharbel.com/s/8qcs3 OpenAI just launched Dots, an always-on AI agent inside ChatGPT that keeps working when you go offline, messages you first, and uses its own cloud computer to complete ongoing tasks. I got access, created my first Dot, connected it to my tools, and gave it a real job. In this video, I show you how the setup works, what OpenAI genuinely got right, where Dots falls apart, and how it compares with Meta Muse, Grok Bot, Hermes Agent, and OpenClaw. Dots runs on GPT-6 Astra, connects to thousands of apps, learns from your corrections, and can work across ChatGPT, Slack, Teams, and voice calls. Its proactive behavior is the biggest difference. It reads the information you give it access to, identifies potential tasks, and starts surfacing useful work without waiting for another prompt. OpenAI also built in sensible guardrails. Background work is read-only by default, so your Dot can research, draft, and plan, but it needs approval before sending messages, posting publicly, spending money, or taking other risky actions. But there are real limitations. Access is restricted by region and plan, completed tasks consume your usage allowance, and the launch arrived alongside major changes to OpenAI’s paid plans. Dots is also entering a crowded market where free and open-source alternatives already offer many of the same capabilitie
Sharbel got launch access, created his first Dot, connected his tools, and gave it a real job — showing the setup, what OpenAI got right, and where Dots falls apart compared with Meta Muse, Grok Bot, Hermes and OpenClaw. First-hand test with a real task.
