Most AI design tools still feel like a one-shot process: write a prompt, generate one image, then start over when you want a new direction.
CapCut Design Studio feels more useful because it brings the creative process into one connected canvas , brainstorming, references, style exploration, layout refinement, edits, and final assets all in one workflow.
That’s much closer to how creators actually design.
https://t.co/HwLE9dz889
Wait… I think I finally get why Chinese AI creators are moving at lightspeed.
They’re not paying full official prices every single time they test an image, video, or entire workflow.
They’re using cost-optimized multi-model API gateways like @toapisai
https://t.co/zQ2Ne6AxA5
I tried it today and yeah… this explains a lot.
50+ top models in one OpenAI-compatible API:
→ GPT Image 2 $0.015/image
→ Nano Banana 2 $0.025/image
→ Seedance, Kling, Veo, Flux & more
This is the AI cost gap most people outside China still haven’t noticed.
What’s the first thing you’d batch-generate if cost wasn’t an issue? 👇
Creative work has always been messy: references, drafts, feedback, iterations, and endless experimentation. Bringing all of that into a single AI-powered workspace is a compelling vision for the future of design.
I asked Agnes AI to build a playable mini-game from one detailed prompt.
Not an image. Not a mockup.
An actual browser game with scoring, timer, movement, restart state, and increasing difficulty.
Built with Agnes-2.0-Flash.
Try Agnes: https://t.co/shJLeDFpAe
@agnesai_sapiens
#AgnesAI #Agnes2Flash #FreeAIModel #AIAgent #MultimodalAI #CodingWithAI #DeveloperTools #NoMorePaywalls #AIWorkflow
This game was vibe coded in 2 days - INSANE how far we’ve come
Model used: muranyi-3: https://t.co/imHOUYRZXy
- Prompts: 39
- Token usage: $90 (so far)
- Starter prompt:
First world prompt for the game:
“Create the Foundation for a third-person 3D high medieval fantasy set in a mountainous open plain with a distant castle landmark.”
First prompt to make the character:
"Okay, I wanna start building a new game and just figuring out a really awesome character to start. A hooded purple wizard with a world-class third-person player and movement system. Decoupled camera versus walking direction, with jogging and walking in all directions with the camera behind the player.”
Tip from our best builders:
Start with 3 to 4 prompts just planning. Tell the AI what your game is, the core loop, the vibe, the genre. Don't rush into building yet. Let the model scope it out with you first.
Once that first output lands, that's when you start iterating. Tweak the animations, shape the world, adjust the UI, dial in the details.
The best games on Tesana aren't built in one prompt. They're built in one conversation.
“Vibe coded” games are getting serious now.
A castle landmark, third-person wizard movement, camera logic, animations, open-world feel — all shaped through one conversation.
The future of game dev won’t be one perfect prompt.
It’ll be builders who know how to steer the AI.
The biggest unlock here isn’t just speed.
It’s that game development is starting to feel like directing instead of manually assembling every piece.
You describe the world.
You guide the loop.
You iterate the feel.
And suddenly a high-fantasy 3D game exists.
This is the part of AI gaming that feels unreal.
Not “make me a game in one prompt.”
But building a real creative conversation:
plan the world, shape the character, test movement, tweak mechanics, refine the vibe.
39 prompts → a playable fantasy game in 2 days is insane.
This is the biggest shift in game development we've seen in years.
From idea → playable fantasy world in just 2 days using 39 prompts.
The real lesson: don't start by building. Start by planning the gameplay loop, world, and player experience. The best AI-built games are created through iteration, not a single prompt.
AI is turning game creation into a conversation.
🔗 https://t.co/cROr5RxfQq…
This isn't just a game.
It's proof that AI is becoming a creative partner, not just a tool.
39 prompts.
2 days.
~$90 in tokens.
The biggest takeaway? The best results come from planning and iterating with AI, not trying to generate everything in a single prompt.
https://t.co/mgpBkSZtzJ
The future of game development looks very different.