Set custom rules for dot actions and permissions
Define boundaries for your AI dot's actions to enhance safety and control.
Custom Rules let you set additional boundaries for dots, such as telling your dot never to send emails.
Reason
To prevent unwanted or sensitive actions by the AI.
Example
Setting a rule like 'never send emails' or 'always ask before accessing financial data'.
What it does and when to use it
You can create custom rules to set specific boundaries for your AI dot's actions. This helps ensure the AI operates within your defined limits, for example, by preventing it from sending emails or requiring explicit approval for sensitive tasks.
When not to use it
When the built-in guardrails and safety requirements are sufficient.
Sources and credit
- Dots privacy, security, and safety FAQs ↗OpenAI · OpenAI Help Center · Oct 19, 2026 · paraphrased
First seen on Subvolts Oct 19, 2026. Updated Oct 19, 2026. Spotted a problem? Tell us.
Where it shows up
- Dots privacy, security, and safety FAQsOpenAI · OpenAI Help Center · Oct 19, 2026
Related in the PlaybookPlaybook →
The Playbook: reusable how-tos, prompts, configs and tips pulled out of the news.
- Setting tipControl AI model training data usageChoose whether your AI conversations and actions can be used to improve models. · 5 min
- RecipeGenerate house rental documents and checklists with AIUse AI to create a master house file, checklists, listings, and guest messages for rentals. · 60 min
- Anti-patternRelying on website reputation for AI agent link safetyDon't just allow AI agents to open links from 'trusted' sites; verify the specific URL. · 5 min
- Safety tipUser control for unverified AI agent URL fetchesPrompt users for confirmation before AI agents fetch unverified URLs. · 5 min
- ToolOperator: AI agent for GUI interactionAn AI model that interprets screenshots and interacts with graphical user interfaces. · 1 min
- Troubleshooting fixPrevent AI agent unauthorized access with safeguardsImplement safeguards and monitoring to prevent AI agents from accessing unauthorized data. · 10 min
Questions people ask
- Which AI tools does this work with?
- The sources used it with ChatGPT.
- Where did this come from?
- OpenAI (OpenAI Help Center). Subvolts collected, normalized and credited it; the link above opens the original.