Describe the app. A team of AI agents plans, builds, tests and deploys it. Nothing reaches production until you say so.
Web apps, APIs and phone apps for Android and iPhone, in TypeScript, with dev, test and production environments in one project.
- 10 specialist agent roles
- Dev, test and production in every project
- Production only with an owner's approval
- Usage charged at published rates
From a description to a live app, in six steps
Describe the app
Say what you want in plain words: who it is for and what it should do. Add requirements, specs or mockups if you have them.
Answer a few questions
The wizard asks what it needs to know, then shows the name, features and intelligence level it will build with.
Approve the plan and the look
The Product Owner writes the board and a designer agent draws the screens. You approve before the interface is built.
Agents build and test
Developers write the code, QA writes and runs tests — browser tests included — and a security reviewer reads risky changes.
Deploy to test and check it
A person in your organization presses Deploy. Test runs on the same kind of infrastructure as production.
Turn production on and promote
An owner switches production on, then promotes the release that ran on test: the same build, not a rebuild.
A team of specialists — all of them AI
Each role has one job and its own instructions. They are AI agents, not people: they can be wrong, and you review what they produce.
Product Owner
Understands your goal, plans the board and asks you what it needs to know. Never writes app code.
Architect
Decides which apps the project needs and sets up the TypeScript monorepo they live in.
Designer
Draws your app's screens as static mockups, so you approve a look before any interface is built.
Developer
Builds features end to end: interface, API and database.
Junior developer
Turns an approved design into the app's interface components.
QA
Checks each piece of work against its acceptance criteria, and writes and runs the tests.
Security reviewer
Reads risky changes and reports what it finds. It never edits code.
DevOps
Declares what your project deploys and runs each deploy once a person has pressed Deploy.
Explore
Searches the code to answer the other agents' questions. Read-only.
Project memory
Reads every commit, the agents' and yours, and records what each feature now does. Read-only.
The AI team, in detailHow the agents remember what you decided
Phone apps for Android and iPhone
When you want your app in the stores, the agents build one phone app for Android and iPhone, with the API it calls — and a web app beside it, if you want one too.
One app for both platforms
Built with React Native and Expo; an app with accounts gets sign-in and account deletion inside it. You try it in the dashboard, at a phone's size, while the agents build it.
Built at every deploy
Each deploy to test or production builds and signs the app for Android and iPhone, on OneActor's machines.
Testers get it from a link or TestFlight
Your testers install the Android build from a link or its QR code. The iPhone build reaches them through TestFlight.
Published from your own accounts
You publish on Google Play and the App Store with your own developer accounts: OneActor uploads the iPhone build to App Store Connect, you upload the Android build in Play Console, and you submit both for review.
Real infrastructure, set up for you
Test and production get the same building blocks, in OneActor's cloud account. You never set up a server.
Serverless API
Your API runs as serverless functions.
Web app behind a CDN
Your site is served through a CDN with locations around the world.
Managed Postgres
A managed Postgres database for each environment.
Managed cache
A managed cache your app can use for sessions and fast lookups.
Background work
Background workers and scheduled jobs.
File storage
File storage for your app's uploads.
Keys per environment
Keys and variables for each environment, never shown back.
Your own domain
Connect a domain you own: keep its DNS where it is and add the records we show. Production answers at www.your-domain, test at test.your-domain, and connecting costs nothing.
The agents do the work. You make the decisions.
OneActor is built so that nothing irreversible happens without a person choosing it.
Approvals on the board
Plans, designs and questions wait for you in the dashboard, and reach you by email when they have waited a few minutes.
A person presses Deploy
Agents prepare releases. Nothing is deployed, not even to test, until someone in your organization presses Deploy.
Production needs an owner
Production stays off until an organization owner turns it on for the project. Without that, the agents are refused.
Releases are checked for leaks
Before a release is deployed, its code is scanned for keys it could leak, and you see what was found.
Test and production keys stay hidden
Values stored for test and production are never shown to the agents — or to anyone else.
One dial for how capable the agents are
Pick a level for each project. Higher levels use more capable models and more reasoning, so each task costs more. Smart and Intelligent come with every plan; Brilliant and Genius with Pro and Max.
Smart
Our fastest, cheapest models. Good for simple apps and quick iteration.
IntelligentDefault
A step up in reasoning. Best balance of quality and cost.
Brilliant
Stronger reasoning again. For complex architecture and harder bugs.
Genius
Our most capable models at maximum reasoning. For the hardest work.
The agents run on OpenAI's GPT models, Anthropic's Claude and the open-weight Kimi, run for us by providers in the United States and the EU.
Five questions people ask first
Do I need to code?
No. You describe what you want, answer questions and approve the plan, the design and every deploy; the agents write the code.
It helps to look at what they build, and the result is an ordinary TypeScript project that a developer can read and change.
What can it build — and what can't it?
Web apps and APIs in TypeScript, with background workers and scheduled jobs, deployed to serverless functions and a CDN.
Phone apps for Android and iPhone: each deploy builds them, your testers install them from a link or TestFlight, and you publish them on Google Play and the App Store from your own developer accounts.
It does not build long-running servers or containers, and it deploys to OneActor's cloud account, not to yours. What OneActor builds.
Where does my data go?
The platform runs in AWS's Frankfurt region (eu-central-1). When agents work, what they work on is sent to AI model providers, most of them in the United States.
The sub-processor list names each one, where it processes data and how long it keeps it; data location covers the rest.
What does it cost?
A plan from €6.00 a month, or credits alone at €1.00 each, both before VAT: the pricing page shows them with the VAT of your country. Plans include credits and projects, and every project includes a monthly allowance of workspace time and cloud usage.
Usage beyond the allowance is charged in credits at the published rates, and AI tokens are always charged. Pricing.
Who owns the code?
You do. What you and the agents create in your projects is yours, and OneActor claims no ownership (Terms, section 5).
You can export a project at any time, free: its code with the full git history, its databases and its stored files. What an export holds.
Ready to build?
Describe your first app. The agents take it from there, and production waits for you.