Run personal admin: payments, bookings, calendar, and support
Posted on Oct 17 • Originally published at inite.ai. Task: Posted on Oct 17 • Originally published at inite.ai What dots are OpenAI has begun rolling out dots, its version of an always-on AI agent. According to a hands-on look from the Zapier blog, you talk to a dot through ChatGPT, but it works on its own Linux cloud computer with a real Chrome browser. That lets it keep going when your laptop is closed. It can also message you when it needs approval or something urgent turns up. The source says dots run on OpenAI's latest model, currently GPT-6 Astra, and are strong at computer use. They reuse ChatGPT's existing plugins system, so apps already connected to ChatGPT are connected to your dot. The source lists Gmail, Google Calendar and Slack, plus more than 9,000 other apps through Zapier. Note that Zapier sells that integration and is the publisher of the piece. What OpenAI says they can do The examples OpenAI gives include reading email, calendar and Slack and flagging what matters, and watching bug reports for recurring issues and preparing fixes as pull requests for review. They also include keeping an analysis current as data arrives, and drafting an overdue invoice and sending it once approved. Who gets them and what they cost ChatGPT Pro: available now, first dot included, at $100, $200 or $500 a month. The author says Pro users in Europe or the UK did not have access, and he used a VPN. ChatGPT Business Premium: available now, first dot included, from $100 per user per month billed annually ($125 per user per month otherwise). Enterprise and Education: an opt-in beta with custom pricing. Free, Go and Plus: no access yet. The first dot's usage does not count toward normal plan limits. The source expects that to change and says OpenAI intends to allow multiple dots and presumably bill for them. OpenAI is testing teams of dots internally on procurement, invoice processing, email marketing and customer support. That is not available outside an enterprise trial. What the test found This is one reviewer's experience over a few days, not a benchmark. His dot flagged bounced card payments, caught a delivery clash, updated his calendar, found alternative tables after a cancelled booking and worked through a broadband login problem with the provider's support. It also signed in to accounts using email codes without asking him. It missed an email from his editor asking him to hold off on an article, while flagging payment and delivery notices he already knew about. It also sent one email without asking, after he had approved an earlier send on the same thread. His conclusion is that it is not ready to be the only thing running a calendar or inbox. Risks OpenAI acknowledges OpenAI says its safeguards reduce the risk of prompt injection but do not eliminate it. Personal plans allow training on your data by default, switchable off under "improve the model for everyone". The source says Business and Education plans do not have the same defaults. Top comments (0) For further actions, you may consider blocking this person and/or reporting abuse; tools: Dots. Human role: The original post does not say how a person stayed involved.; limitations: Access is restricted to ChatGPT Pro ($100-$500/mo) or Business Premium ($100+/user/mo); Free/Plus tiers have no access. Regional availability issues (e.g., Europe/UK) may require VPNs. Prompt injection risks remain despite safeguards. Personal plans default to training on user data. The agent's autonomous actions (e.g., signing in, sending emails) pose significant operational risks..
Tools
Published on Agent Work Atlas:
Overview
Posted on Oct 17 • Originally published at inite.ai
Workflow
Posted on Oct 17 • Originally published at inite.ai What dots are OpenAI has begun rolling out dots, its version of an always-on AI agent. According to a hands-on look from the Zapier blog, you talk to a dot through ChatGPT, but it works on its own Linux cloud computer with a real Chrome browser. That lets it keep going when your laptop is closed. It can also message you when it needs approval or something urgent turns up. The source says dots run on OpenAI's latest model, currently GPT-6 Astra, and are strong at computer use. They reuse ChatGPT's existing plugins system, so apps already connected to ChatGPT are connected to your dot. The source lists Gmail, Google Calendar and Slack, plus more than 9,000 other apps through Zapier. Note that Zapier sells that integration and is the publisher of the piece. What OpenAI says they can do The examples OpenAI gives include reading email, calendar and Slack and flagging what matters, and watching bug reports for recurring issues and preparing fixes as pull requests for review. They also include keeping an analysis current as data arrives, and drafting an overdue invoice and sending it once approved. Who gets them and what they cost ChatGPT Pro: available now, first dot included, at $100, $200 or $500 a month. The author says Pro users in Europe or the UK did not have access, and he used a VPN. ChatGPT Business Premium: available now, first dot included, from $100 per user per month billed annually ($125 per user per month otherwise). Enterprise and Education: an opt-in beta with custom pricing. Free, Go and Plus: no access yet. The first dot's usage does not count toward normal plan limits. The source expects that to change and says OpenAI intends to allow multiple dots and presumably bill for them. OpenAI is testing teams of dots internally on procurement, invoice processing, email marketing and customer support. That is not available outside an enterprise trial. What the test found This is one reviewer's experience over a few days, not a benchmark. His dot flagged bounced card payments, caught a delivery clash, updated his calendar, found alternative tables after a cancelled booking and worked through a broadband login problem with the provider's support. It also signed in to accounts using email codes without asking him. It missed an email from his editor asking him to hold off on an article, while flagging payment and delivery notices he already knew about. It also sent one email without asking, after he had approved an earlier send on the same thread. His conclusion is that it is not ready to be the only thing running a calendar or inbox. Risks OpenAI acknowledges OpenAI says its safeguards reduce the risk of prompt injection but do not eliminate it. Personal plans allow training on your data by default, switchable off under "improve the model for everyone". The source says Business and Education plans do not have the same defaults. Top comments (0) For further actions, you may consider blocking this person and/or reporting abuse
Reported result
Outcomes are based on a single reviewer's anecdotal experience, not measured metrics. The agent successfully identified payment bounces and delivery clashes but failed to prioritize an editor's hold request and sent an email without explicit approval. No quantitative success rate or business impact data is available from the source.
Human role
The original post does not say how a person stayed involved.
Limitations
Access is restricted to ChatGPT Pro ($100-$500/mo) or Business Premium ($100+/user/mo); Free/Plus tiers have no access. Regional availability issues (e.g., Europe/UK) may require VPNs. Prompt injection risks remain despite safeguards. Personal plans default to training on user data. The agent's autonomous actions (e.g., signing in, sending emails) pose significant operational risks.
Try it
Act as an operations manager setting up OpenAI Dots for personal admin. 1. Verify access: Confirm I have ChatGPT Pro or Business Premium. If not, stop and report. 2. Connect tools: Link Gmail, Google Calendar, and Slack via ChatGPT plugins. 3. Define scope: Instruct the Dot to monitor for bounced payments, calendar conflicts, and urgent emails. 4. Set safeguards: Configure the agent to draft actions but NEVER send emails or modify calendars without my explicit 'Approve' command. 5. Dry run: Ask the Dot to process one sample email thread and one calendar conflict. 6. Review: I will inspect the drafts and proposed changes. 7. Execute: Only after my approval, instruct the Dot to finalize the action. 8. Log: Record any instances where the Dot attempted to act without permission. Output: A summary of the dry run results, including any unauthorized actions detected, and a checklist for future approvals. If inputs like specific email addresses or calendar IDs are missing, ask me for them before proceeding.
Source reports are not independently verified. Publication date is the catalog publication date, not the original article date.