What is getting in the way
Sending an unlisted URL is not an access policy. It is hard to revoke, easy to forward, and gives neither you nor the client a clear boundary around identity and authority.
Private client delivery
A client-facing AI agent should verify who is allowed in, keep access revocable, and leave the Agent's instructions, tools, and shared knowledge under your control.
Sending an unlisted URL is not an access policy. It is hard to revoke, easy to forward, and gives neither you nor the client a clear boundary around identity and authority.
Publish the Agent privately, grant exact people or domains through OAuth, or issue a scoped API key when server-to-server access is the better fit.
Private client delivery
Decide whether access belongs to exact verified email addresses, exact normalized domains, or a named API integration.
Use OAuth for people or create a scoped, expiring, revocable API key for an explicit machine-to-machine need.
Confirm the policy before publication, then monitor and revoke grants or keys without rewriting the Agent.
Early access
Yes, with a normalized exact-domain OAuth grant when that policy is appropriate. Similar-looking domains, suffixes, and unverified email claims do not qualify.
No. A standalone Agent remains author-controlled. Clients can use their explicitly owned personal context, but they cannot mutate the shared instructions, tools, Skills, or Agent Knowledge.
Early access
Tell us who the clients are, how they should sign in, and what should remain owner-only. We will map the correct private Agent boundary.