# AI Agent

The AI Agent in Zerve is your supercharged coding and data assistant, designed to help you build, debug, and optimize AI and data workflows seamlessly within the Zerve canvas.

You can describe what you need, whether it is a new workflow, a fix for a broken block, or a change to logic. The agent builds it directly in your workspace. There is no switching tools and no vague suggestions. What sets Zerve apart is the context the agents have.\
\
They understand your pipelines, your data, and your intent. They write code, connect components, fix logic, test their own changes, and create the infrastructure needed to run everything they build.

You can work with one agent or have several collaborating at once. They operate inside the Zerve Canvas, where you can see their plans, make adjustments, or let them complete complex tasks on their own. This setup allows for faster development, smoother debugging, and scalable execution without extra tooling or infrastructure overhead.

Zerve's AI agent can do three main actions : Chat, Search & Code. The agent intelligently routes to one of these functions depending on the task at hand.

To initiate a chat with agent click on the AI Assistance icon on bottom right of the canvas as shown below.

<figure><img src="/files/GhGMtqAPt2dHSP7VqYqL" alt=""><figcaption><p>Initializing a chat</p></figcaption></figure>

To give context to the agent, you upload a file , use voice-to-text or simply write on chat. To use voice-to-text please provide microphone access.

<figure><img src="/files/qDOajnWwkfoSlvRmi10u" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions: 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:

```
GET https://docs.zerve.ai/guide/notebook-view/ai-agent.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.