Everything you'd ask, answered upfront.
We know what you're thinking. Here's the honest answer. Didn't find it? [email protected] real reply, real human.
[email protected]It can't. Every run has a hard per-run spend ceiling enforced between phases. Every LLM call is metered. If an agent overshoots its phase budget, the orchestrator aborts the run and you're only charged for what was actually consumed. No surprise bills.
No. The generated app lands on your GitHub, deploys to your Vercel, and writes to your Turso. If you cancel, you keep the repo, the live URL, the database, the hero images, the marketing copy. Moonshift is the orchestrator. The product is yours.
A live URL, the repo on your GitHub, X + LinkedIn posts drafted, and three hero images. You approve before anything publishes.
Around 8 minutes from prompt to live URL across logged beta runs. Simple landing pages can be faster; complex full-stack apps with auth and payments may take a few minutes more.
Never. Nothing publishes until you approve each post from the dashboard. We draft the copy and images, but you hit the button.
Next.js, React, TypeScript, Tailwind CSS on the frontend. Node.js for backend logic. PostgreSQL via Turso or your own database. Deployed to Vercel by default, with Cloudflare and Netlify as alternatives.
Every run includes automated tests, type checks, and a security scan. If tests fail, the run replays the failing phase. You're shown the issue before anything ships.
Yes. Open any project and describe the change. Moonshift diffs against your existing repo, runs tests, and deploys the update without rebuilding from scratch.
We route prompts across best-in-class models based on the task — planning, coding, copywriting, and image generation each use the model that performs best for that phase. You don't have to choose.
Still have questions?
We're around. Expect a human reply within a few hours.