Creating Cutting-Edge AI Tools for the Gaming Industry: What have we learnt

Johny Darkwah
10 min read

Sometimes you need to be in the right place at the right time. For us, it was an event hosted by an organization called JIC (South-Moravian incubation center), which experimented with the concept of connecting people and companies from the creative industry to those from the tech space. During the event, we met with representatives of a local AAA game studio and discussed about artificial intelligence and its potential for game development. Essentially this was the beginning of a journey that a year later got us a long term project at one of the world's largest game publishers.

We will explore this story in a future article, but today I want to reflect on the experience of the last two years exploring, researching, and building AI tools within the game development industry and community.

Listen and learn, don’t pitch

The Kapnetix team has a lot of experience with AI projects across various industries. The video game industry is quite unique. It’s a rapidly growing industry that is somewhat insular and has evolved its own culture, conferences and networks.

There are several conferences and events in the gaming industry that are focused specifically on developers, publishers, and other industry professionals. Kapnetix had the opportunity to visit the Game Development Conference in San Francisco. These events provide opportunities for industry professionals to network, showcase their work, and learn about the latest trends and technologies in the field.

Breaking into the industry takes a bit of time. A lot of respect is gained from the work done in the industry. Most “about me” slides were a name and a bunch of titles the person worked on. We did have some exposure in game development through a colleague, which helped, but weren't up-to-date with how the industry works these days. Conferences are a good place to start exploring and learning. I typically reach out to a few people and instead of pitching what we do, I expressed my desire to learn. I managed to have a few coffee conversations and naturally the person would ask what I am working on. I typically gave a super short pitch and asked what they thought about the project.

The lesson learnt here is that breaking into the community is hard, especially when you are not a gamer. On the other hand, expressing an honest desire to learn can slowly get you connected. Weeks later, this led to discovery meetings with professionals from EA, Industrial Light and Magic or Disney.

Working with a large game publisher

I read a post from Andrew Chen from a16z sharing some reasons why it's hard for AI companies to break into the gaming industry. One point said:

large publishers often provide tech to their internal studios. They'll partner to learn about AI, but will try to build in-house. Is your tech defensible?

Now we landed a behemoth of a publisher and the experience has been really good. Maybe surprisingly good. The team has openly shared their processes (in our case how they run motion capture pipelines). I’ve never had a sense that the team would be trying to learn and build in-house, but it is a valid point by Andrew. How is our tech defensible?

In my humble opinion, the defensibility will be defined by three things, the uniqueness of the architecture/approach, the quality of data required, and the level of accuracy for the solution to be production ready. Let’s break it down:

We most certainly did not take a model from GitHub or Hugging Face and applied it to the mocap data. Not saying that we haven’t tried, but we were nowhere near the quality and accuracy provided by professionals. We are talking about single digits in mm distances compared to professionals. While we did read a lot of papers, we took them only as inspiration on how to approach certain parts of the mocap cleanup process. To achieve the required accuracy we built the architecture from the ground up.

We achieved over 10x improvement compared to conventional approaches but it did take a year of research and development to get there.

The challenge with data in our case was that the quality of the mocap data we have been using is world class. Meaning it's hard to get outside top studios. In our case, we trained on raw and cleaned pairs of motion capture footage from various parts of the process.

Essentially, most will hit another point that Andrew mentioned

“they also care that their models are trained on data that's safe from a copyright perspective. There's lots of hoops to jump through”

Studios truly view the data created as an asset. Using a model trained on their data for us to monetize is likely to be quickly dismissed. So what do you do? Without data, you don’t have a model, which means you don’t have a product.

One solution is to create your own. In our case, we hired a studio that some of the top studios and publishers outsource to. The key element for us was the experience of the motion capture team. We needed the best possible quality.

Ultimately the lesson learned is that publishers are open to working with startups like ourselves, but the level of quality they need for production ready is really high. One also shouldn’t rely on the fact that every publisher would share their data for model training.

Focusing on quality and time spent rather than saved cost

Anyone following the video gaming community knows that buggy, low quality, or rushed games get ripped to shreds in reviews and forums. This directly impacts sales and in worst case scenarios losses.

We’ve learnt that studios have been adjusting much of their development process to try to mitigate such events. In many cases, it's like a balancing act between time and quality. While automation has been mostly welcomed, there are still cases where developers will want people to spend extra time and care on the job.

This has mainly helped us focus on creating AI that will help solve the “boring” parts of the process. Things that don’t require much creativity, but still cost an immense amount of time. If one has a solution to reduce time with AI automation or generative AI and keep the same level of consistency as professionals, then quite a few inquiries will come your way.


AI has the potential to transform the gaming industry, providing game developers with tools to create better experiences for us gamers. For companies to succeed in this space, they need to be open to learn about the industry and consider what matters to developers as well as studios or publishers.

If you like to hear more, reach out to us at

Johny Darkwah
10 min read

Exclusive Early Access

Don't wait !!! Early adopters will get the best deal on Kapnetix