We are team of two with a design and development background. We have a combined decades experience shipping production-quality code and art. We use AI along with our other tools, like Blender, Substance, etc. to help us build our vision. We use AI in the early stage of concept development and prototyping, coding assistance, but everything that makes it in-game is hand-crafted and authored by us. The music is played by hand real instruments. All screen captures are 100% in-game with no alterations.
We use AI to generate content for the game such as text descriptions, some images like npc portraits and ware items and to generate some stories to create immersion in the game.
We also generate some voicing for dialogs using licensed voices.
We also generate some other sounds such as sound effects (wind, sea waves)
All content text, images, voices or sounds are reviewed manually by a human to verify the content and licensing aspects.
Some graphic and sound assets included in the game were created using generative AI tools during development. The game does not use real-time generative AI and does not connect to external AI services during gameplay.
Generative artwork is used in the creation of part or full of assets that can not be generated by the game engine. AI is used in the drafting of art and writing before it is reviewed and heavily edited.
Some of the pre-rendered 2D art shipped with the game (era intermission illustrations, panel icons, campaign cover images and the Economic Association hall with economist portraits) was produced with generative image tools (fal.ai, Krea) from prompts authored by the developer, then post-processed by hand and by scripts in tools/. No generative AI is used at runtime. The game's simulation code, UI, isometric city renderer, world map (built from Natural Earth data) and all text, including the three interface languages, are authored by the developer.
Generative AI was used to create the game's artwork, audio, localization, and promotional materials. All AI-generated content was personally reviewed, selected, directed, and refined by the developer before being included in the game. No generative AI is used during gameplay.
As an independent developer/publisher, AI-assisted tools have been used selectively to support presentation and marketing workflows, not to replace the game’s creative direction or development.
The game itself is designed, directed, developed, coded, and assembled by human creators. Core gameplay systems, level design, story direction, implementation, and development decisions are not generated by AI.
Generative AI tools were used to create selected pre-generated visual concept art and marketing assets. All AI-assisted material is created before release and reviewed by the development team. The game does not generate AI content during gameplay and does not connect to external AI services during play.
CivEconomy: Future Leader uses locally-running AI for two optional gameplay features. All AI processing runs entirely on the player's machine — no data is sent to external servers.
Text AI (Command Processing): An on-device language model (Llama 3.2 1B via Ollama) interprets natural language player commands and classifies them into game actions. A keyword-matching fallback system works identically without AI enabled.
Image AI (Chieftain Portraits): An on-device Stable Diffusion 1.5 model generates decorative chieftain portrait images. These are purely cosmetic with no gameplay impact.
Both features are completely optional. The game is fully functional and playable without any AI features active.
This game uses pre-generated AI content for a small number of UI button press sound effects created during development using ElevenLabs. These audio assets are included in the shipped game and do not generate dynamically during gameplay. The game does not use live generative AI to create player-facing content while the game is running.
During the process of production, generative AI may be used in following processes: coding and debugging, production of conceptual art of game assets, production of rough models of game assets, production of simple animation effects, restoration of image, audio or video quality, localization and translation. All AI generated game assets that appear directly in game are revised and finalized by real human artists.
This game was created by a solo developer with substantial help from generative AI tools. Every output was reviewed by hand.
Code: Claude Opus 4.8, Claude Fable 5.0
Writing & translation: Claude Opus 4.8, Gemini Pro 3.1
Graphics: Gemini Nano Banana 2
Music: Claude Opus 4.8
Video: Gemini Omni
3d Models for Space Ships created with Meshy.
cooperation in Thinking, design and balance.
C# coding.
Unity Editor Agent for crafting suns and planets out of bought Unity Asset Store Assets.
None of the game's artwork, audio, or imagery is AI-generated. Portraits, interface, and all store and marketing art are hand-authored vector and procedural work, and that is a hard rule of the project. We do use AI assistance during development for writing and code, including drafting store text and the scripts that lay out our marketing art, all of it reviewed and edited by hand. No image-generation models are used anywhere, in the game or in its marketing.
Dialogue and narration are generated at runtime by a small language model running entirely on the player's machine. Nothing is sent to any server. The model has no authority over the game: a deterministic simulation decides every outcome, fact, and number, and the model only phrases scenes from state the engine hands it. Its output is structurally constrained and validated against the simulation before it appears, and invalid output is rejected. Prompts and validation keep generated text within the game's fiction and its PG-13 register. Player-typed orders go only to the local model and never leave the machine.
Bear with me. As a solo-creator I really want to first focus on the game complex logic and its user interface and features, which are crucial to me to give you the best possible experience I can. So this game includes a small number of artworks and music tracks generated using AI tools, which where still edited and refined by me before being included in the final build. I'm working hard to make the game even better at every release. Thank you!
Some static art candidate assets were assisted by generative AI tools during development. Any such assets included in the game are manually reviewed, selected, edited, cleaned, style-matched, and checked before being shipped as fixed static game assets. The game does not use generative AI at runtime and does not generate text, images, audio, video, or other content in response to player input while the game is running.
1. Some character art utilizes hand-drawn original sketches and designs, with AI used for coloring and lighting effects.
2. Background illustrations are AI-generated and then manually refined.
3. The script is AI-generated, with manual editing and content additions.
4. For languages other than Traditional Chinese, AI translation is used, followed by manual proofreading of terminology and content.
Characters, monsters, some buildings, CG images, and logos were generated using AI.
The characters and some 3D building models were created by V2Fun, and the materials are licensed for commercial use under the CC BY 4.0 license.
Some art, music, and 3D assets in this game were created with the help of generative AI tools. Every AI-generated asset was carefully reviewed, refined, and hand-curated by the developer to fit the game's art direction and tone. The game does not use any live-generated (runtime) AI content.
The game calls the aforementioned third-party large language model API over the network at runtime. When the player makes a decision, issues an imperial edict, or interacts with ministers in the game, the game assembles the current situation and character settings into a request and sends it to the AI service; the text returned by the service (minister dialogue, memorials to the throne, plot deduction) is presented in the game interface in real time. This process is transparent to the player and requires no player-side configuration, but an internet connection is required throughout.
I have utilized AI tools to assist in the creation of some store page assets and in-game textures. These AI-generated elements were used as a foundational base, which were then heavily edited, polished, and manually integrated by me to ensure they align with the game's unique art style and technical requirements. No AI tools were used to generate the core gameplay logic or narrative content; their usage was strictly limited to the visual asset production pipeline.
We are team of two with a design and development background. We have a combined decades experience shipping production-quality code and art. We use AI along with our other tools, like Blender, Substance, etc. to help us build our vision. We use AI in the early stage of concept development and prototyping, coding assistance, but everything that makes it in-game is hand-crafted and authored by us. The music is played by hand real instruments. All screen captures are 100% in-game with no alterations.
We use AI to generate content for the game such as text descriptions, some images like npc portraits and ware items and to generate some stories to create immersion in the game.
We also generate some voicing for dialogs using licensed voices.
We also generate some other sounds such as sound effects (wind, sea waves)
All content text, images, voices or sounds are reviewed manually by a human to verify the content and licensing aspects.
Some graphic and sound assets included in the game were created using generative AI tools during development. The game does not use real-time generative AI and does not connect to external AI services during gameplay.
Generative artwork is used in the creation of part or full of assets that can not be generated by the game engine. AI is used in the drafting of art and writing before it is reviewed and heavily edited.
Some of the pre-rendered 2D art shipped with the game (era intermission illustrations, panel icons, campaign cover images and the Economic Association hall with economist portraits) was produced with generative image tools (fal.ai, Krea) from prompts authored by the developer, then post-processed by hand and by scripts in tools/. No generative AI is used at runtime. The game's simulation code, UI, isometric city renderer, world map (built from Natural Earth data) and all text, including the three interface languages, are authored by the developer.
Generative AI was used to create the game's artwork, audio, localization, and promotional materials. All AI-generated content was personally reviewed, selected, directed, and refined by the developer before being included in the game. No generative AI is used during gameplay.
As an independent developer/publisher, AI-assisted tools have been used selectively to support presentation and marketing workflows, not to replace the game’s creative direction or development.
The game itself is designed, directed, developed, coded, and assembled by human creators. Core gameplay systems, level design, story direction, implementation, and development decisions are not generated by AI.
Generative AI tools were used to create selected pre-generated visual concept art and marketing assets. All AI-assisted material is created before release and reviewed by the development team. The game does not generate AI content during gameplay and does not connect to external AI services during play.
CivEconomy: Future Leader uses locally-running AI for two optional gameplay features. All AI processing runs entirely on the player's machine — no data is sent to external servers.
Text AI (Command Processing): An on-device language model (Llama 3.2 1B via Ollama) interprets natural language player commands and classifies them into game actions. A keyword-matching fallback system works identically without AI enabled.
Image AI (Chieftain Portraits): An on-device Stable Diffusion 1.5 model generates decorative chieftain portrait images. These are purely cosmetic with no gameplay impact.
Both features are completely optional. The game is fully functional and playable without any AI features active.
This game uses pre-generated AI content for a small number of UI button press sound effects created during development using ElevenLabs. These audio assets are included in the shipped game and do not generate dynamically during gameplay. The game does not use live generative AI to create player-facing content while the game is running.
During the process of production, generative AI may be used in following processes: coding and debugging, production of conceptual art of game assets, production of rough models of game assets, production of simple animation effects, restoration of image, audio or video quality, localization and translation. All AI generated game assets that appear directly in game are revised and finalized by real human artists.
This game was created by a solo developer with substantial help from generative AI tools. Every output was reviewed by hand.
Code: Claude Opus 4.8, Claude Fable 5.0
Writing & translation: Claude Opus 4.8, Gemini Pro 3.1
Graphics: Gemini Nano Banana 2
Music: Claude Opus 4.8
Video: Gemini Omni
3d Models for Space Ships created with Meshy.
cooperation in Thinking, design and balance.
C# coding.
Unity Editor Agent for crafting suns and planets out of bought Unity Asset Store Assets.
None of the game's artwork, audio, or imagery is AI-generated. Portraits, interface, and all store and marketing art are hand-authored vector and procedural work, and that is a hard rule of the project. We do use AI assistance during development for writing and code, including drafting store text and the scripts that lay out our marketing art, all of it reviewed and edited by hand. No image-generation models are used anywhere, in the game or in its marketing.
Dialogue and narration are generated at runtime by a small language model running entirely on the player's machine. Nothing is sent to any server. The model has no authority over the game: a deterministic simulation decides every outcome, fact, and number, and the model only phrases scenes from state the engine hands it. Its output is structurally constrained and validated against the simulation before it appears, and invalid output is rejected. Prompts and validation keep generated text within the game's fiction and its PG-13 register. Player-typed orders go only to the local model and never leave the machine.
Bear with me. As a solo-creator I really want to first focus on the game complex logic and its user interface and features, which are crucial to me to give you the best possible experience I can. So this game includes a small number of artworks and music tracks generated using AI tools, which where still edited and refined by me before being included in the final build. I'm working hard to make the game even better at every release. Thank you!
Some static art candidate assets were assisted by generative AI tools during development. Any such assets included in the game are manually reviewed, selected, edited, cleaned, style-matched, and checked before being shipped as fixed static game assets. The game does not use generative AI at runtime and does not generate text, images, audio, video, or other content in response to player input while the game is running.
1. Some character art utilizes hand-drawn original sketches and designs, with AI used for coloring and lighting effects.
2. Background illustrations are AI-generated and then manually refined.
3. The script is AI-generated, with manual editing and content additions.
4. For languages other than Traditional Chinese, AI translation is used, followed by manual proofreading of terminology and content.
Characters, monsters, some buildings, CG images, and logos were generated using AI.
The characters and some 3D building models were created by V2Fun, and the materials are licensed for commercial use under the CC BY 4.0 license.
Some art, music, and 3D assets in this game were created with the help of generative AI tools. Every AI-generated asset was carefully reviewed, refined, and hand-curated by the developer to fit the game's art direction and tone. The game does not use any live-generated (runtime) AI content.
The game calls the aforementioned third-party large language model API over the network at runtime. When the player makes a decision, issues an imperial edict, or interacts with ministers in the game, the game assembles the current situation and character settings into a request and sends it to the AI service; the text returned by the service (minister dialogue, memorials to the throne, plot deduction) is presented in the game interface in real time. This process is transparent to the player and requires no player-side configuration, but an internet connection is required throughout.
I have utilized AI tools to assist in the creation of some store page assets and in-game textures. These AI-generated elements were used as a foundational base, which were then heavily edited, polished, and manually integrated by me to ensure they align with the game's unique art style and technical requirements. No AI tools were used to generate the core gameplay logic or narrative content; their usage was strictly limited to the visual asset production pipeline.
CRAGGFALLSteam
