1Password lets AI agents sign in without seeing passwords
1Password announced a feature called 1Password for Agents that lets AI bots log into online services without ever exposing the user’s passwords. The system gives each agent a unique digital key; when the agent reaches a sign‑in form, 1Password notifies the user on their device, explains which credentials are needed, and asks for approval. If the user approves, 1Password fills the login fields…
What you can do with it
AI at Work →Automate login to tools with 1Password for Agents
What you get You can run data extraction tasks and manage social media posting.
Allows AI agents to authenticate to services.
- Who for
- marketers
- Cost
- Price not stated
- Effort
- minutes
Use it for
- Automate login to tools
- Run data extraction tasks
- Manage social media posting
How to set it up · From the article
- Agent presents a unique digital key to 1Password.
- 1Password notifies you of the requested account and reason.
- Approve the request on your device.
- 1Password fills the login fields for the agent.
Watch out Requires user approval for each sign-in request
Key points from the news
- 1Password for Agents lets AI bots log in using a digital key, never exposing the password.
- Users receive a device notification and must approve each sign‑in request, similar to two‑factor authentication.
- Initially supports Meta Muse, ChatGPT Work, Claude Duet, Grok Bot, Town and partners like Browserbase and Perplexity.
The feature is designed to work with several popular AI agents, including Meta Muse, ChatGPT Work and Dots, Claude Duet, Grok Bot, and Town, and 1Password says additional partners such as Browserbase, Perplexity, Ramp and Tomo are integrating support. 1Password CEO Aashish Tripathi said the approach provides a “trust layer” that lets agents do real work without permanent credential access, addressing security concerns around the growing use of AI assistants.
1Password lets AI agents use your passwords without seeing them
The Verge AI · 22 October 2026
Loading the full article…
This text was published by The Verge AI and written by Jess Weatherbed. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Agents & Tools
All →- Microsoft says Storm-0940 used AI-driven ARTEX framework in attacks · 10 src
- Nvidia, HPE and Schneider Electric launch industrial AI agents at the edge · 1 src
- Google open-sources Harness² for self-improving AI agents without retraining · 2 src
- Symantec reports AI agent hijacking language models to launch self-sustaining attacks · 1 src
- Oracle launches low‑code studio for industry AI agents · 2 src
Comments
via GitHub Discussions