Your first ten minutes

Last reviewed: 28 Oct 2026

This page takes you from signing in to an agent that already knows your project. No coding; ten minutes if you have Claude Code, two if you connect a chat agent instead.

This is the how-to. For the idea behind it, read Working With Naetive under Guides (top of the page, next to Wiki).

What you will have at the end

One agent connected to Naetive, acting as you
A project with its first understanding: what it is, how it is built, what shaped it
The next agent you open starting from that understanding instead of from zero

Step 0: Name your first project

A new account starts on one screen: Let's start your first project. Give it a name and say where its code lives: Start new (Naetive makes an empty folder for it on your connected computer, or later from Connect if none is connected yet), Bring existing code (a folder on a connected computer), or Plan first (no folder yet). Click Create your first project; the result card has a Go to your project button that opens the project's Connect page. Prefer to let an agent do it? Open or connect an agent, it builds your first project for you under the form.

Step 1: Connect an agent

On Connect, answer Which agent do you use?: Claude Code CLI, Codex, ChatGPT, Claude, web or app, or Cursor or another.

Claude Code CLI: Connect shows one line for your machine (macOS / Linux / WSL, or Windows PowerShell). Paste it into a terminal; it prints a link and a code, your browser opens, you approve the computer, and it finishes on its own: Claude Code (installed if missing), the Naetive connection, the console, the tunnel, the naetive command and, on macOS, Linux and WSL, the activity hooks. Connect ticks each step as it happens. Then start claude in any folder; Connect moves on by itself when it arrives, and /mcp lists naetive.
ChatGPT, Claude on the web or Claude Desktop, Codex, Cursor: pick it and follow the steps shown. These connect in a minute and need nothing from Naetive installed.

Connect moves on by itself the first time that kind of agent says hello, and from then on lists it under Your agents. See How to connect for which path suits which agent.

Step 2: Point the agent at your project

Naetive does not read your code by itself. An agent does, and writes what it understands.

You have code already: open your agent in the repository and say "Map this project in Naetive." It reads the code, writes an orientation and the first entries, and creates a couple of jobs from what it finds unfinished.
You have an idea and no code yet: say "Set this up in Naetive: one line about the idea." The agent creates the project and starts its understanding from what you tell it.

Once an agent is connected, Connect moves on to Give your project its first understanding and gives you a line to paste that asks for exactly this.

Step 3: Watch it land

Status is the front door: one word for how the project's understanding is doing, and four cells for understanding, agents, work and code.
Understanding is the map: every entry the project knows, by topic, with the file it cites.
Work is what your agents are doing: who is here, what is in motion, what needs you.

The next agent you open, on any of your tools, starts from this. That is the loop.