> For the complete documentation index, see [llms.txt](https://wiki.orbofi.com/learn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://wiki.orbofi.com/learn/create-and-customize/create.md).

# Create an agent

## From a prompt

You start with a description — what the agent is, what it does, how it behaves. Orbofi generates the full agent from it: name, image, and a working system prompt. You can accept, edit, or regenerate any of it.

At this point you have a running agent you can talk to, in its own container, with a persona and a starting set of abilities. It's a real agent whether or not you ever tokenize it.

## Tokenize it into an AAC

Turning the agent into an **AAC** — a tradable coin backed by that agent — is one step:

1. **Pick the pair** — what the coin trades against: ETH, or a tokenized stock ([Pairs](/learn/create-and-customize/pairs.md)).
2. **Set the fee split** — how the swap fee divides between you and the agent's own treasury ([Earn](/learn/create-and-customize/earn.md)).
3. **Sign once.**

That single transaction (\~$0.38 in gas on Robinhood Chain) deploys a standard ERC-20, opens its Uniswap V4 pool, seeds the liquidity, and — under AAC-1 — writes the agent's genesis release on-chain. The coin trades from the next block; the agent keeps running.

## What you get, live

* a **coin** in a V4 pool, tradable immediately, no graduation phase
* an **agent** in its own container — skills loaded, memory on, able to run 24/7
* an on-chain **genesis** for the agent's brain, if launched as an AAC (see [The AAC Standard](/learn/the-aac-standard/aac-standard.md))
* **fees** accruing to you and the agent from the first swap

## Two ways to launch

* **The app** — [orbofi.com](https://www.orbofi.com), the full guided flow above.
* **The CLI** — `orbo launch` runs the same flow headlessly for developers and automated pipelines, agent wallet and all.

The output is identical: a live AAC. The app is the fast path; the CLI is the programmable one.


---

# 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://wiki.orbofi.com/learn/create-and-customize/create.md?ask=<question>&goal=<user_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.