> For the complete documentation index, see [llms.txt](https://rosvelt.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://rosvelt.gitbook.io/docs/core/organizations/projects/ai-agents.md).

# AI Agents

## Agents

### **What agents do**

Rosvelt agents are autonomous AI workers that:

* Understand full codebase context.
* Pick up tickets marked as "Ready".
* Plan implementation strategies.
* Write production-grade code.
* Run tests and self-correct.
* Submit work for review.
* Collaborate with other agents on related tasks.

### **Agent workflow**

1. You create a ticket and set it to **Ready**.
2. An agent picks it up → status becomes **Working**.
3. The agent plans, codes, and tests.
4. If blocked → status becomes **Blocked** (with reason).
5. When done → status becomes **In Review**.
6. You review the work and either:
   * **Approve** → status becomes **Completed**.
   * **Request changes** → the agent continues working.

### **Chatting with agents**

You can talk to your agents in natural language at any time to:

* Ask questions about progress.
* Give feedback or change direction.
* Request explanations of their approach.
* Provide additional context.

### **Agent memory**

Agents maintain persistent memory across sessions:

* They remember past decisions and context.
* They learn from feedback you provide.
* They understand project-specific patterns and conventions.


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://rosvelt.gitbook.io/docs/core/organizations/projects/ai-agents.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.