Skip to content

Tag: professional

A good use case for Claude.ai

I just paid for the premium subscription to Claude AI. Writing certain design documents took me 3-4 days. With Claude, 1-2.

Like every AI, it freaks out a lot. But this help me get started on tasks. I tell it to write me certain spec, it writes me something full of errors and that helps me think. It’s like teaching to a dumb student.

Then, when I have my document with wireframes, I pass it to it and first I tell it to act as a programmer. Again, it hallucinates but it helps me understand the “edge cases” the empty cases that I hadn’t thought of.

Finally, after a second iteration on the document, I send it again and ask to act as a quality assurance professional, to generate a test plan for me. This helps me think carefully about closing all the loose ends.

This is valuable. Indeed.

Playtest what’s wrong to find solutions

A good way to learn more about your game is to keep something that you see as problematic and playtest it. You will discover the obvious, that you need to fix it. But you will also understand much more things behind that.

It happened to me last week, I had the opportunity of running a playtest for my game. And for it I decided to create a specific control system. The developers said “we don’t feel it right”, and me neither.

At the playtest, everyone told me that the system was unconfortable. But I had to see their struggle to decide to take action in first place. In fact, I could notice how they handled the things and that helped me find the solution.

Creating engagement versus finding motivations

When you work for others, very often you are assigned to a project led by a marketing person. Most of the time, you are asked to find formulas to create engagement, addiction, or worse.

However, game design is not this. I don’t know how to define this role of engagement-creator, but it is certainly not game design. It is a magician, perhaps. Or manipulator.

When people say that a game is fun, it is because that game has characteristics that make it enjoyable. But you as a designer do not have a crystal ball, you cannot decide that your game will be fun.

What you can do with your work is find the things that motivate players to play more or complete the game (or parts of it) and enhance them.

Game design is not the creation of the magic flute capable of trapping mice and taking them where you want. Game design is finding the treasure of the duende and digging to bring it to light.

Working with Chinese developers

Since October, I have been working with a company based in Singapore. They hired me as a freelancer for a Telegram instant game, and then we switched to a PC premium game for Steam. Singapore is receiving people from China, they bring their wealth there to be successful.

My teammates are from China, and different regions. I have the pleasure of working with people from a different culture. I am learning a lot, and I want to share some of my early learnings.

The first is their sense of work ethic: they consider the work as a way of contributing to society. They work a lot, also extra hours, because they must do so. Once, I said, “I am sorry, I don’t work on weekends”. I got a private message telling me “Do not work on weekends, ok, but please don’t say it.”

They see themselves as a collective, so if you say you won’t work it’s like you don’t want to support the community.

Second learning: they are very formal and polished in their way of communicating. I use Felo as a real-time translator (they have bad English) during our video meetings. Sometimes archaic expressions pop out. We are so used to the f-word in our colloquial English, we think it’s cool and friendly. Well, not for everyone.

Last, but not least, you should be very clear when something is a suggestion or is an order to execute. If you don’t specify, they will understand that’s an order. They are very vertical in this sense, and it’s hard to have straight conversations with them.

I will keep you updated with new learnings!

LLMs to spot design flaws

I just discovered another interesting use case for current LLM tools. I use Claude.ai at the moment it’s the best in class. I use the free version.

When you design on a document, let’s say a GDD or a one pager for a feature, you should cover the most possible edge cases. In this way, your coders will have everything pretty much clear by reading the document.

If you submit a document to Claude, then you can ask it to simulate the coding in Unity or Unreal Engine for that GDD. It will spit out pseudo code and reasonings. There will probably be lots of hallucinations and things unuseful. Still, there are good chances to discover something you didn’t considered.

Working in a team is self-discovery

Today I discovered something more about myself, thanks to the creative director of the project I am working on with a company.

I tend to not insist too much on my vision. I explain it, defend it, and usually that’s it. When I see too much resistance from the other side, if I have no real power over the decision, I desist and try to meet the boss’ vision.

This is good, but it can lead to a passive-aggressive way of communicating. “I will do like you say, but I do not agree”. At first it may seem like there’s nothing wrong with that, butthe issue is that:

  • it looks like a “ok, whatever” and can damage the relationship
  • it is vague, proposes no real solution, and can damage the project
  • It is not informative enough for the team to make choices on that

Today I have learn something more about myself. Something I want to fix. And that’s why I prefer to work within a team.

Job applications do not work

When I was 20 in Naples, it happened that I was with friends and we met unknown people. And we discover some party at a student’s house to sneak in. Sometimes it went well, others we would find ourselves with very different people. Among ourselves, sitting in a corner, sipping the same beer we had bought to join the party.

Today I don’t sneak in anywhere anymore. I like parties, but I prefer the comfort of being with people I already know. Sometimes I go to strangers’ houses, but in general I like to know a sufficient number of people.

The same goes for job hunting. I prefer having groups of friends in the industry and moving with them. I have a job right now because during the first months of my daughter’s life I played Fortnite at night and wanted to learn how to make levels. That’s how I met the person who then put me in the loop. This is the healthiest way to learn about realities and find opportunities.

Some days are just hard

The game design is a communication job and it’s hard. Communication is one of the most challenging things, because it has a lot to do with perception. Our perception is the way in which we see reality. And it changes according to many factors.

You write specifications and something important gets ignored or misunderstood. Your duty is to report that. They can blame you for not being clear enough.

Sometimes I accept it, some other times I snap. Communication is also to say to someone when they are wrong.

On setting the right expectations

Yesterday I was arguing with a LinkedIn influencer about the expectations that EA had on Dragon Age: The Veilguard. His point was that the game had 1.5M players instead than 3M expected by EA. So the game was lacking appeal for the players.

My point, instead, was that a game that reaches that impressive number (in only 2 months) is definitely an appealing game. Then the game can be good or bad. But for sure it has appeal. The expectations set up by EA execs, instead, were out of reality. The error was theirs, not developers mistake.

He told me that the budget invested in marketing was enormous (no data added) so that the game should have had more players. Plus, the fact of having players doesn’t mean that every player bought the game. That is true, but today if someone decides to invest part of their free time in your game is a miracle. Today we have lots of distractions, it’s hard to reach Elden Ring’s numbers, just to make an example.

The problem is that today we are still setting expectations too high in a landscape with serious distribution and attention challenges. I haven’t played Dragon Age. The Veilguard (I have no time), and I read many different opinions on it. The game is a good game, and it’s appealing. But it was a deception for EA, because of their expectations on it. Those are hard times for forecasters.

Grow your hirings

Every project has a level of learning and skill building for a game designer. It’s very important for a team to be able to guarantee a space for your members to learn. It’s way more optimal to grow your designer than to hire someone already expert, to me.

I say this because the history of games backes my theory. The strongest IPs in the world have been built by people who became experts while they were building.

Many veterans ex-Riot, ex-Blizzard, founded their own independent studios got funded, but they are not delivering too much. Being an expert in something specific brings lots of bias on the table too.

It’s cheaper and safer to grow your people.