Overview
Start here
Getting started
Concepts
Team & ownership
Deployment regions
Guides
Custom domains
Connecting a coding agent ↗Resources
Release notes ↗System status ↗Start here
Getting started
From nothing to a live application without leaving the conversation: connect a coding agent, describe what you want in plain language, and deploy. Even signing up happens right there. You don't need to write code. The agent does the technical work, and you review it in words you understand.
1. Connect your coding agent
A coding agent is an AI assistant that runs on your computer, like Claude Code, Codex, or Copilot CLI. It is how applications get built on Syntica: you talk to it, and it writes, changes and deploys the application. Whichever agent you use, the same Syntica tools plug in.
With Claude Code, one command sets everything up:
$ npx @syntica/mcp setupRestart Claude Code afterwards and you're connected. Codex and Copilot CLI connect through a short entry in their own config file instead. The agent setup guide has the exact snippet for each.
2. Describe what you want to build
Open your agent in an empty folder and describe the application in your own words, the way you would brief a developer:
"Build a portal where our client's field technicians submit inspection reports with photos, and their manager approves them."
"I need an internal tool that tracks purchase requests through three approval steps and emails the requester at each one."
The agent asks clarifying questions, then creates the application: screens, database, logic. Your job is the functional one: check that what it built matches what you meant, and keep refining in plain language ("the approval button should only show for managers"). You never have to read the code it writes.
3. Put it live, account and all
Two steps take it from your machine to a working HTTPS address, without leaving the conversation:
1
Onboard. In Claude Code, run /syntica-onboard. It sets everything up, including your account: signing up for the first time is just answering the agent's questions about your name, email, and an organisation name (the workspace that owns your applications), confirmed with a one-time code sent to your email. No registration form, no password to manage. The same step then registers the application under your organisation and pushes the first version.
2
Deploy. Run /syntica-deploy. It deploys and reports back with a live URL you can open and share.
On Codex or Copilot CLI, the /syntica-* commands don't exist, because they're part of the Claude Code plugin. Just say what you want instead: "set me up on Syntica and deploy this application." The agent walks the same path with the same tools, including signing you up.
Every application gets separate Dev, Staging and Production environments. Work in Dev, show the client on Staging, and deploy to Production when it's agreed. It's the same deploy step, pointed at a different environment.
4. See it in the dashboard
Everything the agent does shows up at app.syntica.io. Sign in with the same email and a one-time code. You'll find your applications, each deployment and its status, logs, and an audit trail of every change. The dashboard is where you manage and verify. Building stays in the conversation with your agent.
Next steps
Invite your team: add colleagues as developers or give clients read-only visibility.
Add a custom domain: serve the application from your client's own hostname.
Guides, including migrating an application off a retiring low-code platform.
We use cookies
We use essential cookies to run the site and optional ones to understand usage. See our Privacy Policy.