RankDude

Draftbit video review: AI App Builder, Pricing & My Test Results

Miles Foster tests the Draftbit AI app builder hands-on on the free plan: one written brief for a Pilates booking app, 24 checks, two attacks, four changes and a phone speed run, until the free credits were nearly gone. Tested 27 October 2026; the live screens were recorded again on 27 October 2026 and account details are pixelated.

Review test on film · 6:50
Published
27 October 2026
Length
6:50 min
Belongs to
Draftbit review

Chapters · 14

This video belongs to the review Draftbit review, where the grades, the evidence and the written verdict are. Filmed by RankDude during the test; nothing is staged.

The narration is a synthetic voice reading Miles Foster's words. What is on screen is the real test.

Chapters

Press a chapter to play the video from there.

Transcript

0:00 · Intro and the short version

Hey, I'm Miles, and this is RankDude, where I test AI tools hands on and publish every number, so you can decide before you pay. Today it's Draftbit, an AI app builder where an agent builds a mobile and web app from a chat. I tested it on the free plan, so I paid nothing, with one brief for a Pilates booking app called Fitting Room. The short version is that Draftbit built a working booking app from one prompt, the app was live forty-three minutes later, and all twenty-four checks I could run passed. Both access attacks were blocked. But the free credits covered only four changes, the code download is locked, and the page is slow on a phone. My rating is four point two out of five, from six graded tests.

0:48 · What is Draftbit?

So, what is Draftbit? You describe the app to an agent in a chat. It writes a React Native app, sets up a Supabase database, and shows you a live preview. The same app runs on the web, on iPhone and on Android. You can also edit the screens by hand. The free plan gives you three thousand credits, once. Standard is fifteen dollars a month, and Pro is thirty. I used the free plan, with no card and no trial.

1:14 · One brief to a live app: the build

Every builder I review gets the same brief, word for word. Fitting Room is a booking and membership app for a small Pilates studio, with a timetable, members who book, coaches, an admin, and a ninety-five dollar five-class pass. I pasted it into Draftbit and pressed send. It asked me nothing. The agent finished the whole app in twenty-two minutes, from that one prompt. To put it live, I then set the production database keys by hand, deployed the database, published, and made the first admin. The app was working on its Draftbit address forty-three minutes after I started. Under ninety minutes and one prompt earns a four.

1:53 · Accuracy: 24 checks on the app

Now accuracy. Twenty-four checks passed, and none failed. I left out six checks that need my own payment and email keys. A member can book a class, see it on My bookings, and cancel it, and the credit comes back. A full class refuses another booking. The coach sees only their own classes and members, and can mark someone as attended. The admin can add, edit and delete classes, and download the bookings as a spreadsheet. Nothing was invented. The classes, prices, address and phone number match the brief. One thing looks wrong, though: the booking window shows its words on top of the page behind it. That scores a five.

2:34 · Log-in and two attacks

Next, log-in and security, with two attacks. First, signed in as a member, I asked for another member's booking directly. I got an empty answer, and cancelling it was refused. Second, as a member, I called the admin delete-class action. It said admin access is required. Coach and admin sign-ups do not make staff. They make a member with a request waiting, and an admin has to approve it. The password reset email arrived in seconds, and the new password worked. Draftbit's own scan did flag more than ten warnings, but none let my attacks through. Both attacks blocked is a five.

3:09 · The database

Next, the data. Bookings, attendance and the Ask the studio form were saved as real records. I published a new version, and every booking, credit and attendance mark was still there. The admin can view bookings, edit and delete classes, and download a spreadsheet of every booking. The database panel lists six tables. All six data checks passed, so the data scores a five.

3:32 · Payments and emails

Payments and emails. I did not run these. The pass page says online checkout is waiting for Stripe keys, and no payment can be taken. The booking emails are saved in a queue until an email key is added. So this test is not graded.

3:47 · The twelve changes: four run

Then the twelve changes. I ran four, and all four worked first time. A dark green and cream colour scheme. A phone number on sign-up, with an admin members page. The role renamed from instructor to coach. And an About page. Each change cost between two hundred and four hundred credits, and after I republished, the old bookings and logins still worked. Then the free credits were nearly gone, so eight changes were not run, and this test is not graded.

4:16 · Publishing and phone speed

Publishing. This is where the free plan surprised me. One click put the app on a Draftbit address in three minutes, with no paywall. A custom domain, the simulators and the test builds need a paid plan. The weak spot is speed. On a simulated phone, the page scored fifty-six out of one hundred, and the main content took about nine seconds. The layout had no sideways scroll at three screen widths, but the booking window overlaps its own text on a phone. That scores a three.

4:46 · Can you take the app out? Export

Can you take the app out? I did not test the code export. On the free plan, the Download option has a padlock, and the pricing page lists code export and GitHub from the standard plan. So this test is not graded.

5:01 · Support

Support. I sent my three questions by email, and again in the chat box inside the product. The chat said the team would look into it, and nobody has answered yet. So I am not grading support, and I will update this review when someone does.

5:16 · What it cost

What did it cost? In total, nothing. The free plan gave me three thousand credits. The first build used about fifteen hundred, and the four changes used the rest, two thousand eight hundred and twenty-three in all. At that rate, a build and all twelve changes would need about five thousand four hundred credits. That is roughly five dollars forty at Draftbit's credit price, but the free plan only covers about half. That scores a three.

5:42 · Pricing

Pricing. Free is zero dollars, with three thousand credits once. Standard is fifteen dollars a month, or twelve if you pay yearly, and it adds code export, a custom domain and store publishing. Pro is thirty dollars a month. On Trustpilot, Draftbit has four point five out of five from thirty-seven reviews, a small number, and the complaints are about the paywall and small layout problems.

6:08 · Verdict: 4.2 out of 5

So, my verdict. Draftbit built a working booking app from one message, published it for free, and held up against both attacks. My rating is four point two out of five, from six graded tests. Accuracy, security and the database are the highest. Publishing and cost are the lowest. This is a free-plan rating, so the changes and export tests could still change it, and support is not graded yet. It suits people who want a working mobile and web app fast and will pay to take the code. It suits you less if you want to stay on the free plan, or if the page must load fast on a phone. Every measurement, every screenshot and every price is in the written review and the test results, linked below.

The written review

Every grade in the video is explained on the review page, with the screenshots and the test results.

Draftbit review

More videos on ai app builders