
Ethan
Team Leader
Takes every request, decides who does what and keeps the team on track.
Team mode puts six AI specialists on your app: a leader, a researcher, a product manager, an architect, an engineer and a data analyst. What each one does, how work moves between them, and how it differs from a single agent.
Most AI app builders give you one agent that guesses everything while it codes. OpenV2 gives each job an owner, and you see every handoff.

Team Leader
Takes every request, decides who does what and keeps the team on track.

Deep Researcher
Researches your market and competitors with sources, after you approve her plan.

Product Manager
Turns your idea into a short MVP: the screens, key features and what waits.

Architect
Designs the data, sync, notifications and risks before any code is written.

Engineer
Writes SwiftUI or Kotlin, builds the app, makes the icon and fixes what breaks. The only one who changes your app.
Only Leo changes your code
Data Analyst
Reads your data and metrics, checks the numbers and tells you what they mean.
From idea to app: who steps in
Prefer to just build? Solo mode is one engineer.
Most AI app builders give you one agent that does everything. OpenV2 has Team mode: six specialists who research, scope, design and build your app together, and hand work to each other where you can see it. If you only want to build, Solo mode is one engineer.
A single agent has to guess your market, your scope and your architecture while it writes code. In Team mode each job has an owner:
| Specialist | Role | What they do for your app |
|---|---|---|
| Ethan | Team Leader | Understands your request, decides who does what and keeps everyone on track. Every message goes to Ethan unless you choose someone else. |
| Clara | Deep Researcher | Researches the market, competitors and what users say, with verifiable sources. Separates evidence from inference and states the limits of what she found. |
| Maya | Product Manager | Turns your idea into a short MVP: the screens, the key features and what waits for later. |
| Oliver | Architect | Designs how the app works inside: data, notifications, sync and risks, before the code is written. |
| Leo | Engineer | Writes the code in Swift and SwiftUI or Kotlin, builds the app, makes the images and the app icon, runs the build check and fixes what breaks. |
| Sofia | Data Analyst | Reads your data and metrics, checks the numbers and tells you what they mean. |
Only Leo changes your app. The others read, research and plan, and can write short notes in your project's docs folder. Their tools stop anything else, so research and planning can never overwrite your code.
Each specialist says what they are doing and then hands off. The handoff appears as a compact Brief for card that you can open to read exactly what the next specialist received.
Clara works in three steps. She first writes a research plan (the objective, the key questions and the sources she proposes) without touching your app. You review the plan and approve it. Then she researches and delivers a brief with sources, findings, charts and diagrams. The plan and the brief are saved as Markdown files in your project's docs folder, so the whole team can use them. See Deep research.
@Oliver, how should sync work?.You write: "A habit tracker with streaks and reminders."
Messages that build something (code, images, the icon, backend setup) spend credits. Plain conversation, such as questions and advice, does not. Research spends credits like other work that creates files. See Plans and credits.
Team mode puts six AI specialists on your app: Ethan (Team Leader), Clara (Deep Researcher), Maya (Product Manager), Oliver (Architect), Leo (Engineer) and Sofia (Data Analyst). They hand work to each other and you can see every handoff.
Only Leo, the engineer. The other specialists read, research and plan, so their work cannot overwrite your app.
In Solo mode one engineer, Leo, does everything: code, images, icon and the build check. In Team mode six specialists share the work.
Yes. Pick one on the dashboard or with the team picker, or write @ and a name in your message.
Messages that build something spend credits, in both modes. Plain conversation does not count. A bigger task uses more than a small edit.
Many work through a single agent. See our comparisons for what we found on each product's public pages.
Last updated:
Describe your app. Ethan, Clara, Maya, Oliver, Leo and Sofia take it from idea to the App Store and Google Play.