What should be different about the UX of AI products?

English

What should be different about the UX of AI products? - (1) Automatic trap

TeamLilys

Feb 2, 20246m

I would like to share what I learned and felt while creating three AI products, Vrew, Rutton, and LilysAI :)

Amazing advances in artificial intelligence are opening up opportunities to ‘automate’ so many human intellectual tasks.

But paradoxically, when our team discusses product UX, we often talk about not falling into the ‘trap of automation.’

When you ask AI to do something, it rarely gets 100 points. Most of them end up only scoring around 70 points.

Wouldn't it be meaningful because it would save a lot of time just by creating a draft with 70 points? You might think: However, as you follow the user's workflow, you often end up having to destroy the 70-point result created by AI and create 100 from scratch in order to achieve the desired goal.

In the case of these types of products, users initially respond by saying, ‘Wow, this is amazing!’, but in reality, they don’t reach a usable level, so retention seems to be low.

We call this phenomenon the ‘automatic trap.’

So how should I fill out the remaining 30 points?

We were able to solve many issues with the engineering and UX layers.

Let’s use our product as an example.

LilysAI is a video summary service.

The summaries were sometimes inaccurate or overly condensed, raising questions about their reliability. When using existing video summary services, I felt the inconvenience of having to watch the video again because there was no action the user could take when the reliability was in doubt.

So, we designed the user experience so that 1) the original script that serves as the basis for the summary is placed right below the paragraph, and 2) the video playback player is always fixed to the left so that the video corresponding to the summary and the summary notes can be viewed together.

As we continue to improve our services with this product philosophy, D+1 Retention started at 30% and is currently increasing to 56%.

One of the most common comments from LilysAI users is, “LilysAI is not a flashy-looking service, but it seems to be the AI product that requires the most work.” I really liked this.

Going forward, we plan to focus more on building a usability layer that truly solves users' problems, rather than on technical keywords that look cool.

If you are a product maker who is interested in our AI product philosophy and are curious to know more, please apply for the position we are hiring for. I always want to meet like-minded people.

/lilys