RankDude

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

Miles Foster tests the Dreamflow AI app builder hands-on on the Free plan: one written brief for a Pilates booking app, 24 checks on the live app, a look at its sign-up, a phone speed run and the paywalls. Tested 27 October 2026. The six graded tests average 2.0 out of 5, and his rating is 2.0 out of 5.

Review test on film · 6:19
Published
27 October 2026
Length
6:19 min

Chapters · 14

This video belongs to the review Dreamflow 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 Dreamflow, an AI app builder that makes Flutter apps. I used the free plan, and gave it one brief for a Pilates booking app called Fitting Room. The short version is that Dreamflow's agent turned the brief into a running app that I had live about twenty-two minutes later, for zero dollars. But it keeps every account and booking in your browser, anyone can sign up as the admin, and the admin screen is empty. Only ten of twenty-four checks passed. My rating is two point zero out of five, from six graded tests. So, what is Dreamflow?

0:49 · What is Dreamflow?

It's an AI app builder that makes Flutter apps. You describe an app in a prompt box, an agent plans and writes it, and you see a live preview next to the code. The plans are Free with ten credits for life, Hobby at twenty dollars a month with a hundred credits, and Pro at ninety dollars with five hundred. I used Free, to see how far it goes and what the paywall stops. Every builder I review gets the same brief, word for word. Fitting Room is a booking

1:18 · One brief to a running app: the build

and membership app for a small Pilates studio, with a timetable, members who book, instructors, an admin, and a ninety-five dollar five-class pass. The first prompt did not build an app. About six minutes later I had a written plan, and a preview that said the project had one error. A second prompt, continue building, took about eight minutes and ended with a running app. I published it about twenty-two minutes after the brief. But only ten of twenty-four checks passed, so the build scores one. Now accuracy. Ten of twenty-four checks passed, eleven failed and three were not

1:54 · Accuracy: 24 checks on the live app

run. Six more checks, the payments and the two emails, need keys that are mine to supply, so I left them out. A member can sign up, book a class, see the booking, and cancel it, and the places go back up. But the first version invented three classes I never asked for, with a made-up instructor and two studios. One fix prompt put the three real classes in. The admin screen is a stub. It says admin tools are next. There is no way to add or delete a class, no booking list, no export, and no Ask the studio form. Accuracy scores two. Log-in, and the two attacks. Sign-up and log-in work, but the roles are only labels. The sign-up form lets anyone

2:35 · Log-in and two attacks

pick member, instructor or admin, and I made an admin account with a new email in one step. The first screen even prints the demo password of every role. And there is no server. The agent saved the users, the bookings and the session in the browser, so my two attacks had nothing to attack. Password reset says a link was sent, but no email exists. This test scores two. Next, the data. One of my six checks passed: a booking was still there after a reload,

3:06 · The database

in that one browser. The admin screen shows no data, so viewing, filtering, editing, deleting and exporting all failed. Dreamflow has Firebase and Supabase panels for a real database. The agent used neither, and I did not connect one, because that needs an account that is yours. The data check scores one. Payments and emails. I did not run them, because Stripe and an email service need keys that are yours to

3:32 · Payments and emails

supply. This test is not graded. Then the twelve changes. I could not run them. The free plan gives ten credits for life,

3:42 · The twelve changes

and the build and one fix used most of them. The one change I did run, replacing the invented classes, cost under two credits and worked first time. This test is not graded. Publishing is one click. I pressed One-Click Deployment, and in under four minutes the app was live on a share

4:00 · Publishing and phone speed

dot dreamflow dot app address. Update Deployment pushes a change the same way. There was no custom domain option. On a simulated phone the home page scored seventy-eight out of a hundred. The page shows a loading screen first and the app after. The iOS and Android tabs say available only on paid plans. That earns a three. Can you take the app with you? Not on the free plan. In the project menu, Download Code is greyed

4:28 · Can you take the app out? Export

out and says it needs a plan upgrade. The pricing page lists code export on Hobby and Pro. So I could not test this, and it is not graded. Support and cancelling. I emailed one question to the support address that serves Dreamflow.

4:43 · Support and cancelling

An automatic answer came in twenty-seven seconds. No person had answered when I made this video, so support is not graded. The free plan has nothing to cancel. The account page has a delete account button, which I did not press. What did it cost? I paid nothing. The free plan gives ten credits for life,

5:03 · What it cost

and four prompts used most of them. Dreamflow's own banner then said I was on course to use two hundred sixty-two credits this period. Hobby has a hundred and Pro has five hundred, so I cannot tell you what a finished version would cost. Pricing. Free is zero dollars with ten credits. Hobby is twenty dollars a month with a hundred

5:22 · Pricing

credits, and Pro is ninety dollars a month with five hundred. The pricing page shows one monthly price for each plan. The prices are clear, but I could not show that a finished app fits in a plan. So pricing scores three. So, my verdict. Dreamflow's agent built a running Flutter app from the brief on

5:42 · Verdict: 2.0 out of 5

the free plan, for nothing. But it looks right and works for one person in one browser. The admin is empty and anyone can become the admin. My rating is two point zero out of five, the average of six tests. Publishing and pricing are the highest grades, at three, and two tests score one. It suits people who want a fast, free Flutter demo, and who are ready to add a real backend. 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.

Dreamflow review

More videos on ai app builders