OpenAI dots + Threads

Threads posts with OpenAI dots and Bolta

Let an always-on ChatGPT agent draft your posts in Bolta, with you approving every one. Parts of the OpenAI dots route are not confirmed yet, and the note below says which. Nothing goes live on Threads until you say yes.

Connect Bolta in ChatGPT first, then add it to your dot. No API key is needed.

OpenAI dotsBolta connected
You

Draft a Threads post about what we shipped this week, under 500 characters, and show me the text first

Illustration of the reply: Bolta returns a draft showing the connected account and the scheduled time, with Approve, Edit and Reject actions.

Illustration. Your drafts show your real text, account and time.

What is and is not confirmed

Read this before you set up OpenAI dots

  • Confirmed by OpenAI: dots are real, always-on ChatGPT agents with their own cloud computer, and you connect apps to a dot through plugins in its profile.
  • Confirmed by Bolta: Bolta is an app in ChatGPT you sign in to with your Bolta account, with no API key.
  • Not confirmed: that the Bolta app shows up under a dot's Customize > Plugins list, and whether a dot can take a custom MCP server address. OpenAI documents neither, so we do not give a custom address or API key route for dots.
  • Not confirmed for Bolta: scheduled runs. OpenAI's getting-started page says you can ask a dot to set a reminder or run a recurring check, but we have not tested a recurring Bolta task on a dot, and the launch post does not mention it.
Bolta on Threads

What Bolta does on Threads

Threads caps a post at 500 characters, and Bolta handles longer text by splitting it into a thread of connected posts, so one long idea does not fail.

  • Text posts, and posts with images.
  • A carousel of 2 to 10 items.
Limits and format

Threads limits and format rules

Network rules last checked 2026-07-28. Bolta's posting rules for your workspace (get-posting-rules) win if they differ from this page.

Not promised for Threads from OpenAI dots: Polls on Threads. Not confirmed for Bolta. Mirroring a Threads post onto Instagram. Threads does not do that on its own, and this page does not confirm that Bolta does it.

Threads limits and format rules
What to knowThreads's own ruleWhat Bolta does
Post lengthA single Threads post is capped at 500 characters, and a reply carries the same limit.Bolta uses 500. Longer text is split into a thread of connected posts.
MediaA post can carry up to 20 photos or videos in one carousel. Video is limited to 5 minutes and 1 GB.A carousel in Bolta takes 2 to 10 items. An image over 8 MB is shrunk if Bolta can.
LinksLinks are allowed, show as a preview card, and are capped at 5 per post.Each Threads link is swapped at publish time for a short Bolta link that counts clicks. If the swap fails, the link goes out as written.
Continuing past the limitYou can continue by replying to your own post, which keeps the follow-on in the same chain.Send a long text as several parts and Bolta posts every part after the first as a reply, which keeps them in one chain.
FormattingNot stated on this page.Plain text only on Threads. Markdown is flattened, and tags and mentions stay as typed.
Best practices

OpenAI dots jobs for Threads, and how to write them

  • Name the Bolta workspace in each brief so the dot drafts for the right brand
  • Reach the same dot from Slack and ask it for a quick post while you are away from your desk
  • Write one longer text when you want a thread, and read where it splits before you say yes.
Prompts

Example prompts for Threads

Things to type in OpenAI dots. Each one asks for a draft and shows you the text first.

Draft a Threads post about what we shipped this week, under 500 characters, and show me the text first

Which of my Bolta drafts are still waiting on a decision, and which one should I look at first?

Write one longer text about our founding story that Bolta can split into a thread, and show it to me before saving

What needs my attention in Bolta this morning?

Review

Bolta saves a draft, you read the exact text, you say yes

  1. 01

    Bolta saves a draft

    OpenAI dots asks Bolta for the Threads post in your brand voice (save-post). A saved draft is never public.

  2. 02

    You read the exact text

    On Threads the exact text includes where a long text is split into a thread and the topic tag, so read each part in order.

  3. 03

    You say yes

    Only then does Bolta schedule or publish (publish-post), in your workspace's timezone. Safe Mode, client sign-off and brand approval rules still apply.

OpenAI dots and Bolta

Using OpenAI dots for Threads

Parts of this route are not confirmed. The note above says which.

For Threads, OpenAI dots, from OpenAI, reaches Bolta through Plugins connected in ChatGPT (custom MCP server not confirmed). Sign-in: Sign in (OAuth). The Threads account itself is connected inside Bolta, not in OpenAI dots.

A dot is an always-on ChatGPT agent with its own cloud computer, so it can draft Threads posts between your chats. Whether it may schedule or publish without asking depends on the dot's own rules, and Bolta's approval rules still apply. Dots depend on plan and region.

An illustration from the OpenAI dots guide, not real output. You ask: How did my posts do last week and what should I post more of? The reply goes along these lines: I pulled your account analytics for the week and can summarise the posts that did best. If you want a follow-up post in that style, I will save it as a draft for you to review. Read only. Draft offered, not made.

An illustration from the OpenAI dots guide, not real output. You ask: Look at my voice settings and write one post in that voice about our new pricing page. The reply goes along these lines: I read your voice context and wrote one draft that follows it. It is saved as a draft only, so nothing is scheduled. Tell me what to change, or say yes to move it on. One draft saved. Waits for your yes.

That matters when you loosen the dot. If you tell it to act freely on drafts, Bolta still refuses to publish what your approval rules hold back. A dot that is told to publish and is blocked by Bolta should say so, and you should read that as the system working.

In practice that means you can send a brief from your phone and look at the result later. The Bolta drafts the dot makes still live in Bolta, so the review step is the same wherever the brief came from.

Bolta's second layer stays on: approval rules, roles and Safe Mode still apply, and a dot rule that says act freely does not switch them off.

  • Draft posts for later review. The dot writes drafts in your voice and saves them to Bolta. This is the safest first job to give it.
  • Read your approval queue. Ask what is waiting for you. The dot lists what it finds and does not approve any of it.
  • The dot looks at your workspaces. It checks where it is allowed to work, so drafts land in the brand you meant.
  • It reads your voice settings. The dot pulls your saved voice so drafts sound like you and not like a default model.
  • Setup: Check you can create a dot. OpenAI says you can create a dot in the ChatGPT mobile app, the desktop app, or on desktop web. Mobile web is not supported. OpenAI points you to chatgpt.com/dots to find a dot you are eligible for. Whether you see dots at all depends on your plan and region, covered further down this page.
  • Setup: Connect Bolta in ChatGPT first. Use the Bolta app link on this page, choose Connect and sign in with your Bolta account. You do not need an API key.
  • API key or bearer header. Not documented for dots. Bolta's ChatGPT route needs no key anyway.
  • OpenAI says a dot has its own cloud computer and keeps working in the background.
  • OpenAI dot. Choose this if you want an agent working while you are away. A dot has its own cloud computer and keeps going between chats. It depends on your plan and region, and the Bolta route inside a dot is not fully confirmed yet.
Connect

Connect OpenAI dots to Bolta

Connect Bolta in ChatGPT first, then add it to your dot. No API key is needed.

FAQ

Threads questions, answered for OpenAI dots

What does Bolta do when OpenAI dots writes more than 500 characters for Threads?
Bolta splits longer text into a thread of connected posts, and the 500 limit also applies to each image caption. The parts are posted as replies in order, so read where the splits fall before you say yes.
Can OpenAI dots reply to someone else's Threads post?
Yes, from a public link (reply-to-social-content). The agent writes the text first with the voice-aware draft tool (draft-engagement-reply) (for a stored opportunity) or (draft-inbound-reply) (for a comment on your own post), shows it to you, and calls reply-to-social-content only after your yes, because that call posts the reply. Finding conversations to join (search-engagement-opportunities) needs a campaign already attached to the account.
I cannot create a dot at all
Dots depend on your plan and region. Pro is for users 18 and over outside the EEA, UK and Switzerland, and on Enterprise, Edu and Healthcare your admin controls whether dots are on. Mobile web is not supported, so use the apps or a desktop browser.
The dot says Bolta is read only
The plugin has been given view permission only. Open the dot's plugin settings, review the permissions Bolta asks for and allow it to act. Saving a draft is an action, so read only will not work.
The dot is connected to the wrong Bolta account or workspace
Disconnect the plugin on the dot and reconnect, signing in with the right Bolta account. Then ask the dot to list your Bolta workspaces and name the one it should use.
The connection worked yesterday and now errors
The connection has probably expired. Reconnect Bolta on the dot. Check your drafts in Bolta afterwards to see what was saved.
Does OpenAI dots publish Threads posts without my yes?
No. Nothing is approved, scheduled or published until you say yes to that Threads post. Whether OpenAI dots completes the connection is not fully confirmed, so read the note above first.

More from OpenAI dots

OpenAI dots can work with the other networks Bolta publishes to. Each page has its own limits and review notes.

Threads from other AI agents

The same Threads limits apply whichever agent asks. The connection and the setup are what change.

Try a Threads draft from OpenAI dots

Connect OpenAI dots, ask for a Threads draft and read the exact text. Nothing goes live until you say yes.