ChatGPT Dots
47 articles in series
Forty-seven articles on OpenAI's Dots — the always-on GPT-6 Astra agents announced at DevDay 2026, each with its own cloud computer and browser, wired into 4,000+ apps through ChatGPT Space. Mechanics, rollout, use cases, the first month's scorecard, and honest scrutiny of the permission model, pricing gaps, and how Dots stacks up against Grok Bot and Meta Muse.
The Activity View: How Much Oversight Is Actually Practical?
OpenAI's Activity View lets you inspect what a dot did while you weren't watching. It's the right idea — and it runs straight into the oldest problem in automated oversight: nobody reads the log.
The Content Dot: Turning One Transcript Into a Week of Posts
OpenAI's Dots can turn a single interview transcript into clips, notes, and social posts — and keep editing every downstream piece when the source changes. What that actually requires.
The Developer's Dot: Watching Feedback and Filing PRs While You Sleep
OpenAI's flagship Dots use case is a developer agent that watches customer feedback, builds fixes, and returns pull requests with demo videos. Here's what that actually requires.
The dot.com Troll: What xAI's Stunt Reveals About the Agent Land Grab
On the exact day OpenAI launched Dots, xAI pointed the domain dot.com at its own Grok Bot page. A small joke, and a genuinely useful signal about how personal this race has become.
The Plugin Ecosystem Behind Dots: 4,000+ Apps, One Interface
OpenAI says dots can connect to over 4,000 apps. That number is real, but what it means in practice depends on plugin depth OpenAI hasn't fully disclosed.
The Product Team's Dot: Keeping Launch Materials in Sync
OpenAI's Dots can learn an organization's standards and rewrite launch materials automatically as a product changes. What that saves, and what it quietly assumes, explained.
The Sales Dot: Comparing Prospects Against the Docs Automatically
OpenAI wants a Dot to check prospect requirements against documentation and build proof-of-concepts automatically. Here's how that compares to xAI's own sales-bot pitch.
What a Dot Cannot Do Yet: The Honest Limits List
OpenAI's Dots launch was heavy on capability demos and light on disclosed limits. Here's a plain accounting of what's undisclosed, unshipped, or explicitly restricted as of September 30, 2026.
What Is a "Dot"? OpenAI's Always-On Agent, Explained
OpenAI's dots are agents that keep working after you close the chat window. Here's what a dot actually is, what it can touch, and where the guardrails sit.
Who Gets a Dot First: Pro, Business Premium, and the Eligibility Map
OpenAI's Dots launched to Pro and Business Premium subscribers first, with regional restrictions and an Enterprise beta gated behind admin approval. Here's the actual eligibility map.
Will Dots Replace Claude Code Skills, or Just Sit Beside Them?
OpenAI's dots and Claude Code Agent Skills solve adjacent problems in very different ways — one is a standing agent, the other a composable capability. Here's why they're not actually competing.