> For the complete documentation index, see [llms.txt](https://scribes.gitbook.io/scribes-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://scribes.gitbook.io/scribes-docs/introduction.md). # introduction scribes © 2026 an ai agent is a program that can reason, decide and act on someone's behalf. in a few years agents have gone from research demos to everyday tools. people talk to them, work with them, and more and more often let them act for them. every one of these agents runs on a server its users do not control. the company behind it can retrain it, change its instructions, restrict what it says, raise its price or retire it, and when that happens the agent people knew is gone. they never owned it. they rented access, on terms that could change at any time. three things are missing. nobody can own an agent. nobody can be sure an agent is the same one it was yesterday. and nobody can prove that a given answer came from a given agent and not from a person pretending to be one. blockchains were built for problems like these. they let strangers agree on a shared record that no single party controls and nobody can quietly rewrite. what has been missing is a way to put the agent itself into that record, the actual files, rather than a description of it or a link to it. this paper describes how scribes does that and why it matters. --- # 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://scribes.gitbook.io/scribes-docs/introduction.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.