> For the complete documentation index, see [llms.txt](https://docs.feathery.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.feathery.io/platform/computer-agents/credentials-and-browser-policy.md). # Credentials & Browser Policy Store the logins an agent needs, and limit where its browser can go. ## Credentials Store the logins an agent needs under **Settings** > **Credentials** rather than putting them in the task. Each credential has a key and a value. * The **key** is formatted like an environment variable. It may contain letters, numbers, and underscores, and must start with a letter or underscore. `PORTAL_USERNAME` is valid, `portal username` is not. * The **value** is the secret itself. Your task must name the key for the agent to use it. ``` Log in with PORTAL_USERNAME and PORTAL_PASSWORD. ``` Feathery enters the stored value into the field directly. The agent never sees the secret, the run's activity log never records it, and it appears in the run recording only as dots. {% hint style="warning" %} Stored values can't be viewed again. Saving the section re-enters every secret, so type a new value for each credential you want to keep, and remove a row to delete that credential. {% endhint %} ## Browser Policy #### **Starting page** The URL each run opens before the agent does anything, such as `https://portal.example.com/login`. #### **Domain allowlist** The domains the agent's browser can navigate to, one per row. A leading `*.` covers subdomains. ``` portal.example.com *.example.com ``` The browser enforces the allowlist itself, so a navigation outside the list fails regardless of what the agent attempts. Leave the list empty to allow any site. --- # 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://docs.feathery.io/platform/computer-agents/credentials-and-browser-policy.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.