Weekend service, or review of AI tools for product creation

Now they are trying to automate everything with the help of AI: from programmers to consultants, and doctors. The number of startups and services for this is increasing year by year. How good are these tools and is it possible to abandon the product team and replace it with a couple of services for $20 a month? Let's try it!

I was sitting last weekend, thinking about what to do with myself, and decided to set myself a challenge: to create a web service with some real value, without writing a single line of code. You can see the result of this herespoiler – it turned out acceptable. If you want to repeat this experiment yourself, then my review of all automatic services is at your service.

UI/UX services

It always seemed to me that the most difficult part for automation was the work of the designer, including UI/UX. For the code, everything is clear – it’s just a language in which even GPT-3 could say something, but can a robot write a symphony and all this… It turned out that it very much can – with big reservations, but everything is in order.

Let's go through all the services with the same prompt: compare visual results, ease of use, and, of course, cost.

Our prompt

First page

I am developing a web app focused on generating vocabulary for language learners. Design the main page, which should display topic cards (each featuring a name and image) along with the language level. The cards must be organized into groups based on the language. The overall design should be modern and minimalistic.

Second page

Now, design the second page in the same style. This page will be for simple “choose the correct answer” tasks. It should include the following:Task text and multiple-choice optionsTask number (eg, 1/10)Progress barTopic name

v0

v0 – a relatively new (only a year old) tool aimed purely at creating pages. He can write in React, Tailwind CSS, and Shadcn UI.

The interface is similar to ChatGPT+Canvas. On the left side we prompt, and on the right you can change the code and look at the resulting result.

The interface is similar to ChatGPT+Canvas. On the left side we prompt, and on the right you can change the code and look at the resulting result.

Trial: Eat. It's unclear how many messages there are per day
Pro version:
20$/month, gives 100-200 messages per day

  • A very minimalistic tool that is not difficult to understand

  • Keeps a consistent style quite well

  • All generated code is available and can be edited in the built-in editor

  • Killer feature – the resulting site can be immediately published and given access via a link. It is clear that complex logic is unlikely to be implemented, but for one-page or profit center it is good

Our home screen

Our home screen

Screen with tasks

Screen with tasks

Galileo AI

Galileo AI more like dribbble, behance and all these social networks. networks for designers. There are many examples of already generated projects, which does not leave you with a blank sheet of paper, showing the capabilities of the tool at one time. By default, all designs you generate also end up in the public collection.

Get inspired by examples or create your own design using a prompt.

Get inspired by examples or create your own design using a prompt.

Trial: Eat. About 15 generations in total
Pro version: 16$/month – 120 generations per month, 32$/month – 300 generations per month.

  • The ability to generate not only using a prompt, but also an image. Can be useful when you already have a project and need to add something in the same style

  • Each generation offers two different interface options.

  • Can be generated separately for Mobile and Web

  • All generated code is available, you cannot edit it

  • You can change the design using prompts, but the model is not very responsive – I asked her to remove several buttons and she did not remove all of them

  • Killer feature – transfer the design directly to figma

Home screen

Home screen

Screen with tasks

Screen with tasks

Wizard

Wizard – more like a co-pilot for designers than “Press one button and you’re done.” There is an opportunity to edit the resulting design not by prompts, but almost like in Figma. Because of this, using it for our purposes… is not so convenient.

On the left is the development panel, in the middle are our screens.

On the left is the development panel, in the middle are our screens.

Trial: 3 generations per month
Pro version: 12$/month – 500 generations per month, 32$/month – 5000 generations per month.

  • On the plus side: it generates the entire work flow for our service at once: from the landing page to the class calendar

  • Of the minuses: I didn’t ask for this at all, it’s a very big overload for my tasks. A good example, of course, of possibilities, but it would be even better if it were possible to control this behavior

  • The colors are also strange. Can you read what is written in white font on the acid green buttons?

  • There are a lot of bugs: in order to generate one page, I had to reload the site 5 times and start generation again: somewhere it refused to place the design on the canvas, somewhere it simply gave a generation error.

  • The source code is available, but only on the pro version

  • There are a lot of features for design: turning photos into components, design reviews… In general, professionals would probably appreciate it?

  • Opportunity to work as a team on one project

Our main screen. If Artemy Lebedev did this, how much would he charge?

Our main screen. If Artemy Lebedev did this, how much would he charge?

There is no second screen – it started giving an error, and thank God – the first one was enough for us to draw conclusions.

UX Pilot

UX Pilot – also a kind of co-pilot for design, but with a simpler structure than the previous hero. There is also autoflow (automatic generation of a sequence of screens), but there is much more control – each screen is described before generation and you are given the opportunity to change this description.

Only the panel with prompts is a true AI tool. What they do additional training on, however, is an interesting question if there is no possibility of manual editing.

Only the panel with prompts is a true AI tool. What they do additional training on, however, is an interesting question if there is no possibility of manual editing.

Trial: About 12 generations
Pro version: $9/month: export to Figma, to code, number of projects and screens without restrictions.

  • Good autoflow, you can reduce your cognitive load at the stage of thinking through the sequence of screens

  • Editing with prompts is quite accurate

  • There are other features for the UX product: design review, heatmap, interviews with AI users (what?)

  • Source code and export to Figma are available, but only on the pro version

  • Interactive design – you can poke buttons

Home screen

Home screen

Screen with tasks

Screen with tasks

Relume

I heard about Relume good reviews and that it is often compared to UX Pilot. It is a direct competitor to the previous one: the same simple design, generating everything using prompts, but there is the possibility of collaboration and figma elements: the design can be edited together and more precisely, without using prompts.

Relume allows you to precisely determine the structure of pages before generating them

Relume allows you to precisely determine the structure of pages before generating them

Trial: 1 page and one project – home
Pro version: $18/month – 1 project, 5 pages. $40/month – no restrictions.

  • Autoflow control thanks to sitemap – determination of what will be in text form and where

  • Editing using prompts and manually

  • Source code and export to Figma are available, but only on the pro version

  • Interactive design – you can poke buttons

  • Collaboration with the team on the project

  • The trial version is very strictly limited – you can’t do anything other than landing on it

  • There are training videos – it will be easier for beginners to get used to it

  • Even despite my prompt, it stubbornly generated the home page as a landing page. I don’t know if the problem is with this free version and other pages don’t have this, or if the AI ​​is not very smart

  • Killer feature – integration with webflow, that is, you can make a design here and host your project on webflow. I don’t know, though, whether you’ll have to pay for a subscription there too

He refused to generate anything other than a landing page... At least the landing page is good, but without pictures

He refused to generate anything other than a landing page… At least the landing page is good, but without pictures

Total

I liked UX Pilot the most, although v0 sounds like it would be good too, but it is unclear how well the model will be able to cope with a large number of pages. Current models can generate visuals for projects quite well, but I wouldn’t use it anywhere other than MVP, or I would, but with the intervention of a designer.

This was the first part. I wanted to add the entire work flow here: from design to DNS, so to speak, but the first part already turned out to be quite voluminous. If you were interested, leave a comment or support with a reaction – I’ll make a second part about the backend and with the help of what services this design can be turned into something full-fledged.

By the way, I completed the challenge – I uploaded the project with cards to the Internet in two days without writing a single line of code. You can read about him here.

Similar Posts

Leave a Reply

Your email address will not be published. Required fields are marked *