OpenAI launches dots agent to handle ongoing tasks without human input
OpenAI introduced dots, an always-on AI agent designed to manage long-term tasks without constant human oversight. Unlike ChatGPT, which requires repeated instructions for updates, dots operates autonomously within defined boundaries, using GPT-6 Astra and integrating with over 4,000 apps via plugins. It can adjust work dynamically—such as updating documents after new data arrives—while…
Key points
- Dots uses GPT-6 Astra to handle ongoing tasks without repeated human prompts, integrating with 4,000+ apps
- OpenAI limits autonomy with boundaries for automation, approvals, and human oversight for critical steps
- Available to Pro/Business Premium users in stages, with Enterprise beta access; no extra fee for first dot
Users set parameters like autonomy levels, approval requirements, and task limits. Dots is currently rolling out to Pro and Business Premium subscribers in select regions, with Enterprise users able to opt into beta versions. No additional cost is charged for the first dot, though usage limits apply. The feature is only available via the desktop app or web for now.
Model page: GPT-6 Astra →
The story so far
5 episodes →- OpenAI launches dots agent to handle ongoing tasks without human inputthis story
Stop telling AI to continue every time work changes. Leaving the rest to ChatGPT 'dots'
note.com · 30 September 2026
Loading the full article…
This text was published by note.com and written by AIまかせ研究所. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
Coverage and discussion
2sourcesThe headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Amazon releases Strands Decider 2B, a Jev-inspired open-source decision model · 2 src
- Decagon launches Voice 3 agent with Chord speech model for multilingual calls · 2 src
- Nvidia researchers improve AI agent reliability with a judging model · 1 src
- NVIDIA neom agent toolkit uses Amazon s3 vectors for agent memory · 1 src
- Anthropic deploys Claude buying agent to handle inbound sales · 2 src
Comments
via GitHub Discussions