> For the complete documentation index, see [llms.txt](https://build.intract.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://build.intract.io/users-hub/ai-agents/warden-your-privacy-agent.md). # Warden: Your Privacy Agent Imagine you join a new app—like one for rides or games. You skip the “Terms & Conditions” because it’s long and boring. But buried in there, the app gets permission to grab your emails, watch what you browse, or share your location with others. Soon, you’re hit with annoying ads or weird emails. Sound like something you’ve seen? You’re not alone. **More than 60% of people** don’t read those terms, but in 2022, **almost 422 million personal records** got exposed in data breaches (says the Identity Theft Resource Center). It’s not just spam—sometimes it’s serious stuff like your address, credit card, or even doctor records getting out ### What Warden Does **Reads Terms for You:** Warden quickly scans the confusing “Terms & Conditions” and tells you simply: “This app wants your contacts and location all the time. Okay with that?” If you say “No,” Warden stops it for you. **Stops Old Apps:** That budgeting app you forgot about? It might still be snooping on your bank. Warden finds these sneaky connections and lets you cut them off fast. **Checks the Dark Web:** If your password or credit card info is being sold online, Warden warns you right away—no waiting until weird charges show up. **Easy Privacy Check:** Warden gives you a clear list of who’s using your data. If something looks off—like a game tracking your location—you can stop it with one tap --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://build.intract.io/users-hub/ai-agents/warden-your-privacy-agent.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.