Allow
The request goes through as usual.
Free tool · no signup
Pick what your app holds. Get rules for what your customers' AI agents may see and do, and a policy file you can ship.
| Resource | AI agent | AI browser | Not sure | Person |
|---|---|---|---|---|
Profile and contact detailsprofile.read | Allow | |||
Customer lists and searchcustomers.search | Allow | |||
Documents and statementsdocuments.read | Allow | |||
Exports and CSV downloadsreport.export | Allow | |||
API keys and tokensapi_keys.read | Allow | |||
Deleting recordsrecord.delete | Allow | |||
Users, roles and invitesmembers.manage | Allow | |||
Account and security settingssettings.update | Allow |
Tap an answer to change it.
AI agent permissions · B2B SaaS or CRM · Balanced · Watch first Profile and contact details AI agent: sees it with private fields hidden AI browser: sees it with private fields hidden Not sure: can read it Person: can read it Customer lists and search AI agent: sees it with private fields hidden AI browser: sees it with private fields hidden Not sure: can read it Person: can read it Documents and statements AI agent: is refused AI browser: waits for the owner's passkey Not sure: can read it Person: can read it Exports and CSV downloads AI agent: is refused AI browser: waits for the owner's passkey Not sure: can read it Person: can read it API keys and tokens AI agent: is refused AI browser: is refused Not sure: waits for the owner's passkey Person: can read it Deleting records AI agent: is refused AI browser: can ask; the owner approves each one with a passkey Not sure: can ask; the owner approves each one with a passkey Person: can do it Users, roles and invites AI agent: is refused AI browser: can ask; the owner approves each one with a passkey Not sure: can ask; the owner approves each one with a passkey Person: can do it Account and security settings AI agent: is refused AI browser: can ask; the owner approves each one with a passkey Not sure: can ask; the owner approves each one with a passkey Person: can do it AI agent: proven agent activity in the session. AI browser: an AI app's browser, no agent action seen yet. Not sure: too little signal, never treated as a person. Made with https://onehuman.ai/ai-agent-permissions-generator
Free for 30 days. Watch-only first, no card.
Rules for what an AI agent may do with your customer's login. Each action gets one of four answers.
The request goes through as usual.
The page loads, private fields come back empty. The agent can still help.
The request waits until the account owner approves it with a passkey. An agent cannot approve itself.
The agent is refused. A person takes the session back with a passkey.
The same customer can be at the keyboard one minute and hand over to an agent the next. So each rule answers per situation.
Agent tool traces in the page, a signed agent request, or clicks no hand could make.
The page is open in an AI app's browser, but nothing shows an agent acting yet. The person's first real click unlocks it.
Too little signal. Never treated as a person.
Human clicks or a passkey. Always allowed.
The balanced defaults the generator starts from. A person is always allowed.
| Data or action | AI agent | AI browser | Not sure | Why |
|---|---|---|---|---|
| Money dataBalances, statements, transactions | Mask | Mask | Allow | Read-only money. Masking keeps the page usable. |
| Personal dataNames, contact details, ID documents | Mask | Mask | Allow | Regulated data. Agents summarise it and pass it on. |
| Lists and searchCustomer lists, CRM search | Mask | Mask | Allow | One pass reads every record. |
| Medical or HR dataMedical records, salaries | Block | Mask | Allow | The most sensitive data an app holds. |
| Files and exportsDocuments, CSV exports, downloads | Block | Ask owner | Allow | One click hands over the whole dataset. |
| Keys and passwordsAPI keys, tokens, recovery codes | Block | Block | Ask owner | Must never reach a model. |
| Moves moneyTransfers, orders, refunds, payout details | Block | Ask owner | Ask owner | Hard to reverse. A hidden instruction on a web page can trigger it. |
| Deletes or changes settingsDeletes, roles, invites, security settings | Block | Ask owner | Ask owner | Hard to undo, and it changes who has access. |
Something missing? Write to arif@onehuman.ai.
Rules for what an AI agent may see and do when it acts with a customer's login in your app. Each action gets one answer per situation: allow, mask, ask the owner, or block.
No. It is for the agents your customers bring into your app with their own login. For agents you build, give each one its own identity and scopes in your authorization system.
Scopes cover apps a customer connects to your API. A browser agent never asks for a scope: it uses the customer's own browser, cookies and login. So the rules have to work inside the session, per request. How OneHuman does it →
Claude in Chrome, Claude desktop, ChatGPT agent, OpenAI Codex, Perplexity Comet, Playwright and Puppeteer. What each one does against a protected page →
Rarely. A person is always allowed, and their clicks are checked as they happen. In our tests 2 of 397 human clicks were read as a program. Start with watch first to see every decision before anything is enforced. How we measured →
The request is held. The account owner approves it with a passkey (Touch ID, Windows Hello), and the approval covers only that request: same action, same amount, same recipient.
Yes. The plain-English rules work as a spec for any stack or a security review. The JSON file is OneHuman's policy format, and npx onehumanai init puts it to work on a Node.js server. Read the docs →
No. The generator runs in your browser. The share link keeps your choices after the #, which never reaches a server.
Nothing up to 100 customers a month whose AI agents use your app. You pay only for those customers. Pricing →