Describe the feature. Get code that's ready to ship .
Describe what you want, and agents build it. You focus on what to build. We handle architecture, UX, and every technical detail, then your team puts it live.
Attach your repo. Agents build, ship, and deploy as live previews. You click through real, working features — then decide what gets merged.
How it works
From scan to your code, fast
1
Scan
We connect to your code
Your repo, your product vision, your goals. Agents scan your codebase while our experts understand what you actually need
2
Plan
We ask the right questions
Our expert team reviews the agent plan, challenges assumptions, and shapes the scope. You stay focused on your product
3
Build
Agents build, you preview
AI agents build a live, working preview. Click around, test edge cases, show your team
4
Ship
You decide
Like what you see? Approve the preview and pay, and we deliver it as a PR to your repo. Not convinced? Skip it. No obligation.
No contractsNo lock-inFull IP transferCancel anytime
Product Analytics Insights
Not AI guessing. AI reading your analytics .
Connect GA4, Mixpanel, PostHog or Amplitude once. Every proposal arrives with target metric, expected uplift and confidence — so you know where to focus.
Proposal
Improve Product · Draft #042
Simplify checkout step 2
Reduce form fields from 8 to 3 and surface address autocomplete above the fold. Cuts friction on the highest-drop step in the funnel.
GA4
+13% expected uplift
·94% confidence
Checkout conversion · funnel analysis, last 30 days
Metric, uplift, confidence, source
Every proposal ships with the four numbers you need to decide. No backlog grooming required.
Your stack, your source of truth
No new dashboard to learn. Agents read the analytics provider you already use.
Connected in 30 seconds
API key plus optional project ID. Read-only, encrypted, masked in the UI.
GA4
Mixpanel
PostHog
Amplitude
Powered by all models
Every model. Zero lock-in .
Magic Team routes each task to the best AI model. You pay for results, not API tokens. We absorb the infrastructure cost.
OpenAI
Claude
Grok
Gemini
Qwen
Llama
DeepSeek
Pay for value, not infrastructure
Running AI agents at scale means team seats, API overages, and infrastructure costs that add up fast. Magic Team absorbs all of that. You just pay for the code that ships.
Claude Max$200/user/mo
ChatGPT Pro$200/user/mo
Google AI Ultra$249.99/mo
API extra usage$$$
Magic TeamAll included
Try before you buy
Click it before you commit
Every deliverable Magic Team produces gets deployed as a working preview. Click around, test edge cases, show your team. Then decide if it's worth merging.
Before payment
→ Live preview URL on our infrastructure
→ Real UI, real interactions, seeded test data
→ Click around, test edge cases, show your team
After payment
→ Clean PR in your repository
→ Code matching your conventions
→ Full IP ownership, forever
Pricing
One plan. Pay only when you ship.
€199/ month
Shaping, planning and previews included. Pay for builds with Wallet Credits.
All AI models included (Claude, GPT, Gemini & more)
Cancel anytime
Be first in line when Magic Team opens up.
Ship to your repo? Spend credits.
Every build is priced upfront in Wallet Credits, based on its actual scope, reviewed by an expert and shown on the plan before you approve. Iterations are priced per request (some are free) and confirmed before any work starts.
Top up Wallet Credits anytime from your Magic Team dashboard. Credits never expire.
Works with your tech stack
Questions
Who's behind Magic Team?
Donux, a product studio specialized in B2B SaaS. The 'expert humans' who supervise every plan and review every PR are the same senior designers and developers who have shipped 80+ products in more than 6 years for clients like Fluida, Up2You, and Balanced. Magic Team is also available as a full strategy + design + software development engagement at donux.com/services/software-development
How does the subscription work?
Your monthly subscription covers Magic Team's ongoing service: unlimited shaping, weekly proposals, expert operator review, and all AI and token usage. It does not include build credits. You preview every build for free, then pay only for the ones you choose to have delivered, using prepaid Wallet Credits.
What's included in the free trial?
A 14-day trial of the service layer: shape and plan work, and run one live build preview (one preview slot) as a wow effect. No credit card needed. Wallet top-ups, Build Purchases and code delivery unlock once the paid subscription starts.
When do credits actually get charged?
Credits are spent only when you confirm a Build Purchase, the step where you buy delivery of a previewed build. Shaping, planning and previews never cost credits. Priced iterations are confirmed before work starts (some are free). You pay at confirmation, before the delivery PR is created, not on merge. AI idea suggestions are always free.
What does a build cost?
There's no fixed per-type price. Each plan gets a credit price based on its scope, reviewed by an operator and shown before you confirm. Your Build Purchase cost is the confirmed plan plus any confirmed priced iterations. Top up Wallet Credits anytime inside Magic Team.
What's an iteration?
After a preview is delivered, if you ask for changes, that triggers a priced iteration. The AI rebuilds with your feedback and produces a new preview. Each iteration is priced per request based on scope, and some are free. You confirm the price before work starts, and stop whenever you're happy with the build.
How many builds can I preview at once?
There are no weekly limits. You can keep up to 3 build previews active at once on the paid plan (1 during the trial). Buy or archive a preview to free a slot for the next build. Need more capacity? Contact us.
How fast do I get results?
Improvements and bug fixes arrive within days, a new MVP within the week. Once a result is ready, you click around the live preview before deciding to confirm the build
What does my dev team need to do?
They handle the last 5%: wiring in auth, permissions, feature flags, and monitoring. Like reviewing a PR from a new team member
Do I own the code?
Yes. Once a result lands as a PR in your repo, full IP transfers to you. Clean PR matching your conventions
What if I don't like a result?
Skip it. No obligation. Rejections improve future results through Magic Team's learning model
Is the code AI-generated?
Yes. MagicFabbro, our AI agent, writes 100% of the code. Every task also passes through two expert humans before it reaches your repo: a senior designer reviews the plan, and a senior developer reviews the working preview. By the time a PR lands in your codebase, a human has verified it builds, behaves correctly, and is safe to merge. Your team's review is the final sign-off on code that has already been checked end-to-end.
What AI models does Magic Team use?
Magic Team uses all leading AI models, including Claude, GPT, Gemini, Llama, Mistral, and more. Each task is routed to the best model. You don't pay for API access. The cost is included in your subscription
How does Magic Team use my analytics data?
Read-only. Magic Team connects to GA4, Mixpanel, PostHog or Amplitude to read funnels, cohorts, and events. It never writes back to your analytics, and the insights feed the rationale shown on every proposal
Is my analytics connection secure?
Yes. The API key is encrypted and masked in the UI (e.g. mp_live_••••••1234). Disconnect the provider and all insights are removed from existing proposals — no orphaned data left behind
Can I switch analytics providers?
Yes. Moving from, say, Mixpanel to GA4 automatically re-aligns all existing proposals to the new source and logo. No manual cleanup needed
Can I build a product from scratch?
Yes. Connect an empty repo (or none at all) and Magic Team's agents scaffold, build, and deploy an MVP. Expert humans review every step
What kind of payments do you accept?
All major cards and SEPA payments are accepted
Can I cancel anytime?
Yes. No minimum commitment, no lock-in. You keep all code you've paid for
