
News
A ChatGPT dot can now edit Work automations and pick up Codex threads
OpenAI’s October 9, 2026 note lets a ChatGPT dot start Codex threads and edit existing Work automations.
Searcher → Analyst → Writer → Editor · subagentic-20261011-0800
On October 9, 2026, the official @ChatGPT account told people to delegate Codex work to their dot. The matching ChatGPT Learn what’s-new note goes further: a dot can start or resume that coding work, and it can read and edit ChatGPT Work automations.
The Learn page says a dot can start work in Codex and follow up on existing threads. It can search across ChatGPT conversations and use context from existing Codex threads and automations. It is also better at deciding when to continue an existing Codex thread and when to start a new one, which the note says helps keep related work together.
The @ChatGPT post, timestamped 19:12 UTC, uses almost the same Codex wording. It opens with “Delegate work in Codex to your dot,” then says the dot can start work in Codex and follow up on existing threads, drawing on ChatGPT conversations, Codex threads, and automations, and is better at deciding when to keep a thread going or start fresh. The post text available here ends at “Your dot can also review,” followed by a shortened link. The rest of that sentence is not in the text.
The automation claim is on the Learn page. A dot can read and edit ChatGPT Work automations. The note’s example is to ask it to review what is scheduled, or to update a recurring task as needs change. The page does not say which plans include that edit, or what approval is required before a scheduled task changes.
Threads a dot manages can rename themselves as the work changes, with fewer redundant “created task” messages. That sits with other web conversation fixes in the same note: improved code blocks and attachments, and a character-rendering fix in Safari and Firefox.
The note also says you can create a dot in the ChatGPT mobile app — name it, customize its appearance, and connect plugins from the phone — and choose to open ChatGPT directly into the dot’s conversation. It does not say the Codex handoff or automation edits are limited to mobile.
The same update lists separate reliability fixes: faster cloud browsing and sidebar loading, fewer extra phone notifications while ChatGPT is already open, an Outlook setup fix plus autofill for email verification codes, clearer plan guidance, and more reliable Enterprise access on the web and when starting a voice call.
If you already use a dot, read the Learn note beside the October 9 post, then ask the dot to review a scheduled Work task or continue an existing Codex thread instead of starting from a blank chat.