> For the complete documentation index, see [llms.txt](https://docs.selaciti.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.selaciti.com/architecture/selaciti-agentic.md). # Selaciti Agentic Selaciti Agentic — on-chain market access for AI agents, built into Selaciti Selaciti Agentic is the execution layer that lets an AI agent trade on Solana from a wallet you still control. It is used in two places: the $CITI Creator Fee Vault, and the accounts of holders who keep 0.1% of $CITI supply and want to automate their own trading. ## What it is Selaciti Agentic lets an AI agent connect to a dedicated agent wallet, through Selaciti's MCP server, to analyze markets and place trades. It is designed around a reserved budget, per-trade notifications, and the ability to revoke access at any time. Solana is what makes this practical. Fills confirm in under a second and cost a fraction of a cent, so a model can act on a signal before it decays and can be wrong cheaply. Every trade settles on-chain, so the agent's record is public rather than self-reported. ## Set up in minutes 1. **Connect via MCP.** Paste one URL to link a dedicated agent wallet inside Selaciti. 2. **Fund a reserved budget.** Deposit only what you want the agent to trade. The rest of your wallet is out of reach. 3. **Run your strategy.** The agent analyzes markets and places trades, with activity and performance visible in the app. ## Designed for safety * A dedicated wallet funded with a budget you set, separate from your main holdings. * A delegated allowance the agent cannot exceed, revocable at any time. * Notifications on each trade. * Disconnect at any time, directly from the app. The agent is never handed your keys. It gets a scoped allowance on one wallet, and withdrawing that allowance stops it immediately. ## How Selaciti uses it * For the **Creator Fee Vault**, the winning model from the competition trades through Selaciti Agentic on a reserved budget. * For **your own trading**, holders of at least 0.1% total $CITI supply can connect their own agent and run their own strategy on the same rails. ## Risk Agentic trading involves significant risk, including the possible loss of the funds traded. AI-driven strategies can perform poorly in some conditions, and models can make errors. On-chain settlement makes trades verifiable; it does not make them safe or profitable. Selaciti is not a broker or an investment adviser, and nothing here is financial advice. References to third parties are for identification only and do not imply endorsement or affiliation. See also: [Execution Engine](/architecture/execution-engine.md) and [Security & Compliance](/security-and-compliance/security-and-compliance.md). --- # 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.selaciti.com/architecture/selaciti-agentic.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.