1Password, an Identity Security provider, has announced Secure Agentic Autofill, a new capability designed to securely deliver credentials to AI agents operating within web browsers, initially available through an early access integration with cloud browser automation platform Browserbase.
Secure Agentic Autofill enables AI agents to authenticate with web services without exposing user credentials. This integration allows AI developers to link a 1Password vault to power secure browser workflows, providing IT and security teams with assurance that sensitive data and credentials remain protected through 1Password’s security infrastructure for Agentic AI.
David Faugno, CEO of 1Password, commented on the development, stating, “AI is opening up new ways to help people work smarter and get more done, but the fundamentals of security don’t change. At 1Password, we have always believed security should empower productivity, not block it. By partnering with Browserbase, we’re making it simple for teams to build and innovate with Agentic AI while keeping credentials and sensitive data protected by default. That way, you can focus on creating real value, knowing agentic AI identity security is built in by default.”1Password’s approach to AI incorporates principles of privacy, transparency, and trust, extending them to Browserbase. Secure Agentic Autofill ensures AI agents can execute workflows under human oversight, with credentials remaining private and unexposed. Business and consumer app developers can connect their 1Password vaults, define which credentials AI Agents can access, and enable secure autofill only when necessary. Key features include human-in-the-loop authorization via 1Password mobile or desktop, credentials remaining private and unshared with LLMs or Browserbase logs, simplified setup, just-in-time authentication for login credentials and Time-based One-Time Password codes at runtime without secret storage, and automatic credential mapping to prevent phishing.
The introduction of Secure Agentic Autofill addresses a critical challenge in AI adoption: secure authentication. As AI agents increasingly perform actions on behalf of users, they require secure login capabilities without constant human intervention. Current practices in AI development sometimes lead to embedded secrets within agents, potentially compromising security. This new capability delivers credentials directly from a 1Password vault into Browserbase at runtime, under human oversight, utilizing end-to-end encryption and 1Password’s zero-knowledge security model. This ensures secrets are not visible to or processed by the AI, offering a safer method for organizations to integrate AI agents.
Paul Klein, CEO of Browserbase, highlighted the importance of this partnership, noting, “We see AI agents changing the way work gets done, from procurement and onboarding to customer service and research. As we move toward an AI-native internet, these agents need a trust layer for credential access. Our partnership with 1Password creates exactly that, extending their proven security framework into the emerging world of agentic browser automation, so organizations can scale AI confidently.”Secure Agentic Autofill will be available in early access starting October 8, 2025, for 1Password customers utilizing Browserbase. 1Password is recognized as an Identity Security leader, trusted by over 175,000 businesses and millions of consumers. The company pioneered Extended Access Management (EAM), a cybersecurity category designed for both human and AI agent workflows, securing sign-ins across all applications and devices, including those unmanaged by traditional tools.
Browserbase provides cloud browser infrastructure, trusted by over 1,000 businesses and developers, including AI leaders such as Perplexity, Vercel, and Commure. The platform offers scalable, fast, and secure cloud browsers, enabling thousands of browser instances for web automation, testing, and AI agent workflows.
