Put your dot on call
OpenAI YouTube 104,549 views as of 17 October 2026
Why it is here
OpenAI’s 3-minute film: Ali, an OpenAI engineer, uses his dot to triage an on-call incident at 3am; the dot investigates and starts a Codex thread that he steers from the ChatGPT app on his phone. About 105k views in a day.
Description
Description written by Gemini from the videoGemini 3.8 Flash, 17 October 2026
Summary
Ali Shobeiri, an engineer at OpenAI, demonstrates how he integrates OpenAI’s “dots” (persistent cloud agents) into his engineering workflows. He shows how to connect a dot to Slack and configure it to automatically monitor alert channels and triage on-call pages into actionable Codex investigation threads across mobile and desktop.
What is shown
- Slack Setup: In the Codex desktop app, the presenter connects his dot to Slack, assigning it a dedicated user identity (
alishobeiri-dot) so teammates can tag it in threads [00:20–00:39]. - Automation Setup: Entering an automation prompt in the Codex composer: “Monitor the [channel-name] channel and any incoming page I get, please triage the page and create a thread to investigate” [00:48–01:04].
- Mobile Alert & Triage: The presenter demonstrates receiving an on-call page on his phone, opening the ChatGPT mobile app, and viewing the dot’s completed automated investigation and summary under an
Investigate cloud thread failuresCodex thread [01:12–01:33]. - Desktop Sync: Continuing the investigation by viewing and steering the exact same Codex thread seamlessly on his laptop [02:08–02:13].
Claims & numbers
- The presenter describes dots as persistent cloud agents with their own cloud computer, access to the user’s local computer, and their own identity across third-party services like Slack [00:06–00:16].
- The presenter claims the dot autonomously triaged an on-call page received at 3 AM, diagnosed what went wrong, created the Codex thread, and allowed him to resolve or monitor the incident directly from his phone without getting out of bed [01:09–01:56].
- The presenter mentions other workflows, such as setting up automations to triage incoming customer feedback channels or tagging the dot in Slack to open pull requests and iterate on code [02:18–02:29].
Notable quotes
- “We built dots to be a persistent cloud agent that has its own cloud computer, but also has access to your local computer and has its own identity across all these different services that you already work, such as Slack.” [00:06]
- “My dot’s already done the investigation, figured out what’s going wrong, and it’s also created a Codex thread for me that I can actually click into and start to steer the thread...” [01:25]
- “At 3 AM I don’t need to go out of bed and grab my laptop and start to investigate this incident, because it’s already done the investigation for me.” [01:49]
Assessment
An official product demo from OpenAI showing real UI interactions within the Codex app, Slack integrations, and the ChatGPT mobile app. The demonstration presents a genuine walkthrough of setting up agentic automations, though the 3 AM on-call triage scenario is recounted retroactively using saved message logs and pre-recorded threads.
Described by gemini-3.8-flash on 2026-10-17 from the video’s audio and frames.
Related
More videos on this
-
A total disaster
The PrimeTime1,070,298 views as of 15 Oct
-
OpenAI Dots Failed Live on Stage
SAMTIME993,531 views as of 15 Oct
-
Introducing dots, always-on agents built to handle everything.
OpenAI719,658 views as of 13 Oct
-
Live from OpenAI DevDay 2026: Keynote
OpenAI672,946 views as of 13 Oct