Orca ADE Tutorial: Build A Website With 4 Agents

The fastest way to learn this orca ade tutorial is to pick a real thing to build, so that is how I have written it.

Orca is a free, open-source agentic development environment.

You download the app, open a project, and run as many coding agents side by side as you like.

Rather than listing menus, I am going to walk through four builds I have actually done in it — a website, a mobile app, an internal tool, and a scheduled automation.

Each one teaches a different part of the environment.

The Base Setup Every Build Shares

All four builds start the same way, so here is the common ground once.

You download the app from the Orca GitHub repo.

You open a project, which you can do by browsing to an existing folder, cloning from a GitHub URL, or creating a brand-new project from scratch.

You open an agent in the terminal — Claude Code, Codex, Hermes, Kimi, OpenClaw or Antigravity.

Then you right-click and split the terminal right or down, a few times, until you have four agents working the same project at once.

That is the base.

Everything below is what you do with it.

🔥 Want these builds handed to you as templates? Inside the AI Profit Boardroom I give members 1,000+ done-for-you AI agent workflows, the full Agent OS zip, daily tutorials and 5 live coaching calls a week. 2,800+ members already building with them. → Get access here

Build 1: A Website (The Best First Project)

A website is the ideal first build because it exercises the preview, element select and annotations all in one sitting.

Set the panes up with different jobs

I ran Claude Code in one pane and Hermes in another.

One agent handled layout and structure.

The other handled copy and styling.

That split alone removes most of the waiting, because neither agent is queued behind the other.

Get the preview live before you build anything

Ask the agent you are coding with to give you a localhost URL.

Click the plus sign at the top and choose new browser tab.

Paste the localhost URL and the site renders inside Orca.

Do this early, not late.

Watching the site change while the agents work is the entire reason to use this environment over a plain terminal.

Use element select instead of describing things

I did not like the logo on the first pass.

Rather than writing a paragraph about which logo and where, I selected it, pasted it into the coding agent, and gave feedback on that one element.

No ambiguity, no wrong-component edits, no wasted turn.

Batch your feedback with annotations

Right-click anywhere on the preview and describe the change.

"Make the headline bright yellow" is the level of detail needed.

Then pick your intent — a command if you want it changed, or a question if you want the agent's opinion on what would work better.

Adding an annotation does not fire immediately, which is the point.

I marked up ten things across the page, hit send once, and the agent worked through the entire list in a single pass.

The free version of this build

Here is where it gets interesting for anyone without subscriptions.

I gave two setups the same prompt — create a beautiful website for an SEO agency — and on that run the free Ling 3.0 output looked a little nicer than the Claude Code version.

That is one test on one day, not a league table.

But it means a website build in Orca can cost you literally nothing and still look good.

If you want more on the free-agent side, my Hermes installation guide covers the agent I used.

Build 2: A Mobile App

The mobile build is nearly identical, with one requirement you need to know before you start.

You do not use a browser tab for the preview.

You open a mobile emulator instead — an Xcode emulator or an Android Studio virtual device.

One of those two is required for mobile previews, so install it first rather than discovering it mid-build.

Everything else carries over.

The split terminals still give you parallel agents.

The annotation workflow still applies to what renders in the emulator.

For a website, a game or a tool, you never need the emulator at all.

Build 3: An Internal Tool Driven By Computer Use

This is the build most people do not realise Orca can do.

From the terminal you press enter and the skill installs.

Computer use lets agents control any app on your machine.

Orchestration lets several agents coordinate rather than trip over each other.

With computer use enabled, your agents stop being limited to writing files and start being able to drive the software around the project.

That turns a coding environment into something closer to an operations environment.

If that idea is new to you, my breakdown of OpenClaw computer use shows what agent-driven desktop control looks like in practice.

There is voice in there as well, though I do not personally use it.

Build 4: A Scheduled Automation

The automation panel lets you schedule recurring agent tasks, and this is the build that runs without you.

You can have an agent iterate and improve a project every single day.

You can have it research a topic and draft a post on a schedule.

The honest catch is that your computer needs to be running for scheduled work to fire.

This is local scheduling rather than a cloud service, so treat it as a desk-hours automation and plan around that.

Where it earns its place is compounding work — small daily improvements on a project you would otherwise never get back to.

Build	Preview you need	Key features used	Cost
Website	Browser tab (localhost)	Split terminals, element select, annotations	£0 with Hermes + free API
Mobile app	Xcode or Android Studio emulator	Split terminals, emulator preview	£0 plus emulator install
Internal tool	Browser tab or none	Computer use, orchestration skills	£0
Scheduled automation	None	Automation panel	£0, machine must stay on

How To Do Any Of These Builds Completely Free

There are two honest routes, and both cost nothing extra.

Route 1: Plug in subscriptions you already pay for

If you already have Codex, Claude Code or OpenClaw, connect them.

Orca itself is free and open source, so you pay exactly what you paid before.

For most people that is the fastest path to a working setup.

Route 2: A free agent plus a free API

No subscriptions? Use a free agent with a free API.

In my own run I used Hermes with a free API — Ling flash — and it genuinely cost nothing.

People always push back and say it is not really free.

It is. Free agent, free API, free environment.

If you want a second free pane alongside it, my post on getting Claude Code free covers that route too.

🔥 Want to build these with me rather than alone? Inside the AI Profit Boardroom I run step-by-step tutorials on exactly these builds — free API setups, parallel agents, and the annotate-and-batch workflow — plus weekly live coaching with 2,800+ members. → Get the free agent build stack here

Orca Mobile: Running Builds Away From The Desk

You scan a QR code and can then run your terminals and projects from your phone.

I have not put it through its paces properly yet, so I am not going to oversell it.

What I will say is that I have tried remote coding through other tools and found it underwhelming every time.

Being able to drive several agents across several projects from a phone is a better shape of idea than the single-chat remote apps I have used before.

Where Orca Fits Alongside An Agent OS

Orca is excellent at what it is: an environment for parallel coding agents.

It is not trying to run your whole business, and it does not claim to.

That is the job of an Agent OS — the wider agentic operating system where Hermes runs with shared memory, a mission-control dashboard, and skills for content, SEO, research and publishing.

You use Orca when the work is building software.

You use the Agent OS when the work is running the business around it.

The two sit together nicely, which is exactly how I run them.

Frequently Asked Questions

What is the best first build for this orca ade tutorial?

A website. It uses the live preview, element select and the annotation queue in one sitting, which is most of the tool learned in an hour.

Is Orca really free?

Yes. Orca is free and open source. You either plug in subscriptions you already have, or run a free agent with a free API like Hermes with Ling flash. Neither route adds cost.

Which agents can I run side by side?

Claude Code, Codex, Hermes, Kimi, OpenClaw and Antigravity among others. You add, enable and disable agents in the settings and can run several at once on the same project.

Do I need an emulator?

Only for mobile app builds, where an Xcode emulator or an Android Studio virtual device is required. Websites, games and tools preview in a normal browser tab.

Can Orca automations run overnight?

Only if your computer stays on. Scheduled agent tasks fire from your machine rather than from a cloud server.

What does the computer use skill add?

It lets agents control any app on your machine, so they can drive software around the project rather than only writing code inside it. You install it from the terminal by pressing enter.

About Julian

I'm Julian Goldie — AI entrepreneur, SEO expert, and founder of the AI Profit Boardroom (2,800+ members). I help business owners scale with AI agents, automation, and SEO.