The system sets up communication among the agent, the user, and the password manager.
When an agent tries to log in, the user gets an alert and can personally approve the request.
1Password then fills in the credentials on the agent's behalf so it can finish the task.
In a blog post, 1Password said that handing over a password is a common shortcut, but it can leave sensitive information in places people can no longer control, because a copy may be saved for later use.
The company says its product gives people a trusted way to delegate tasks while keeping control of their passwords, secrets, and credentials.
The news came the same day Axios reported that U.S. banks have begun detecting agentic activity inside customer accounts. The report suggests this is not necessarily rogue agents stealing from accounts, but a sign that consumers are letting automated services act for them, including on financial matters. The main problem, according to the report, is that most banks cannot tell whether such activity reflects a customer's request. Bankers interviewed by Axios called the situation "horrifying," and a Chase spokesperson said customers "should not give their usernames and passwords to anyone."
Users can choose which agent to use with 1Password for Agents, including Anthropic's Claude Duet, OpenAI's Dots or ChatGPT Work, Grok Bot, Meta's Muse, and agents from the AI assistant startup Town. 1Password says it is working with other companies to expand the service.