×

Dynamic AI
Co-Creation

A Human-Centered Approach
by Will Luers

Created through the Digtal Pubishing Initiative at The Creative Media and Digital Culture program, with support of the OER Grants at Washington State University Vancouver.

publisher logo

Chapter 5: AI World-building

1. Imagined Worlds

From the surreal alien encyclopedia of the Codex Seraphinianus to the immersive fantasy realms of Tolkien, Le Guin, and Star Wars, great world-builders use rich detail to transport us into entire imagined universes. Today, AI tools offer new ways to participate in this tradition—not just for storytelling, but as a way to explore how multiple creative systems can work together.

Curious Archive | Encyclopedia Of A World That Doesn’t Exist: Codex Seraphinianus

World-building is more than inventing settings—it's an ideal way to learn how AI can help with complex creative tasks. From research, writing to image generation, audio design, map-making, and even basic coding, AI can support every stage of building a fictional world. This makes it a perfect exercise for learning how different AI tools work together and how to guide them with a clear creative vision.

Students engaging in AI-powered world-building will practice valuable skills: doing research, generating consistent lore, designing visual styles, and even building customized GPTs for creative or organizational tasks. It’s an all-in-one training ground for developing real-world AI fluency.

At its core, great world-building starts with a spark—an image, an idea, a feeling—and expands into a coherent system of places, cultures, histories, and rules. Each choice should build on what came before, creating depth and consistency. Like cultural anthropologists of their own imaginary worlds, creators must balance logic with imagination. The best worlds don't just entertain—they surprise us, reflect our values, and offer new ways of seeing the real world.

Ted-Ed | How to build a fictional world - Kate Messner

2. AI Worlds

Language Models and Generative AI open up many possibilities for creative world-builing within many different contexts. A movie production might use AI generators to work out the look, feel and compositions of shots well before any actual shooting. Video Game designers already use AI for responsive and interactive elements in gameplay. An historian might want to work with students to research and model an ancient city. Together, human and machine, can elaborate on conceived environments, characters and histories at a speed and scale exceeding our individual faculties.

Because AI generators are good at following specific tasks, human creators who can articulate with prompts and meta-prompts what they want can achieve remarkable representations of complex worlds. Precise language and detailed prompts are key. These creators can guide the AI to generate more specific details and make corrections by refining their prompts iteratively. For example, if a creator envisions a desert city with towering sandstone structures, they can start with a basic prompt and gradually add details about the architectural style, the types of plants in the oasis, or the way the light reflects off the buildings at sunset. By continuously adjusting the prompt, the AI can produce images that closely align with the creator’s vision.

But human co-creators who are not sure about what they want can also use AI generators to explore and iterate through possibilities. AI processes facilitate human imagining, especially for creators who may not have a vivid mental image of their world. Such creators can use AI as a brainstorming partner. They can start a chat by asking broad questions about a possible world, such as "What kind of civilizations could exist on a planet with three moons?" The AI can provide suggestions and options, helping the creator explore different traits and characteristics. This iterative dialogue can help creators discover aspects of their world they hadn't initially considered. For instance, they might ask, "What flora and fauna would thrive in a jungle with bioluminescent plants?" and then refine their ideas based on the AI's responses.

3. Brainstorming Chats

More than just straightforward text generation, AI language models excel as creative conversation partners to help brainstorm and refine the high-level foundations underlying an imagined world. By engaging in iterative dialogue, creators can envision:

  • The origin stories and fundamental conflicts that shape a world's history and cultures
  • The diverse sentient species, their physiologies, traditions, and societal norms
  • The geographic and climatic features that influence resource distributions and migratory patterns
  • The systems of magic, technology, and power dynamics governing civilizations
  • The rich diversity of world's flora/fauna, languages, religions, and more

Rather than static worldbuilding guides or setting bibles, this dynamic chat process allows creators and AI to develop a shared context spanning the world's deepest roots to its furthest branches. The humans supply visionary sparks which the AI then expands into elaborated, internally cohesive concepts to consider and refine.

Unlike working alone, this symbiosis benefits from AI's ability to hold vast knowledge spaces and generate logical extrapolations - freeing the creator to prioritize higher-level oversight, quality evaluation, and maintaining a unified creative voice.

4. Creating a Custom GPT

CNET | How to Make a Custom GPT for Anything: ChatGPT Creator Tutorial

While general-purpose AI tools are helpful, building your own customized GPT unlocks a much deeper, more personalized creative collaboration. With ChatGPT Plus (GPT-4 or GPT-4o), you can create a custom GPT that’s fully aligned with the world you're trying to build.

The process starts by giving your GPT a clear identity: you define how it should speak, what knowledge it should prioritize, and the kind of help it should offer. For example, a sci-fi world-building GPT might be instructed to focus on plausible technology, alien cultures, and speculative linguistics, while a fantasy GPT might emphasize mythic structures, magical systems, or poetic descriptions.

To make your GPT truly useful, you can upload reference materials like maps, timelines, glossaries, artwork, and background lore. These help the model understand the internal logic and style of your world. With each interaction, you can refine its output by giving feedback—adjusting tone, accuracy, and world-consistency. Over time, this turns your GPT into a kind of co-author or creative assistant that gets smarter and more aligned with your vision.

This kind of tool is not just about convenience. It’s about building a shared creative intelligence—an AI that grows with your project. It can help brainstorm factions, generate location descriptions, maintain consistency across cultures or timelines, or even simulate dialogues between characters. The result is a smoother, more efficient creative workflow—and a world that feels richer and more coherent.

5. Meta-Prompting Strategies

Meta-prompting is an advanced technique that lets world-builders create layered, evolving fictional worlds by turning AI’s outputs back into new inputs. Instead of writing one-off prompts for isolated answers, meta-prompting builds a feedback loop—where each response shapes what comes next.

For example, you might start by asking the AI to describe a fictional civilization. Then, using that response, prompt it to generate cultural traditions that would logically emerge from that civilization’s values. From there, ask how those traditions affect future technologies or political systems. The result is a world that grows organically, with each layer building on the last.

This recursive process mimics how real cultures evolve—through adaptation, memory, and self-reference. Meta-prompting can produce surprising complexity, where past events influence future developments, myths evolve over generations, and societies react to their own histories.

Using meta-prompting, the AI becomes a kind of simulation engine, helping you generate not just isolated details but entire systems of belief, behavior, and consequence. With each iteration, your fictional world becomes more coherent, unexpected, and alive.

6. Unit Exercise: Designing a Near-Future AI-Entangled World

This unit guides you through the collaborative process of imagining a near-future society shaped by human-machine relationships. Using AI tools, you’ll explore how systems of governance, labor, ethics, and everyday life might evolve—and how creative world-building can help us think critically about our own futures.

  1. Define a Focal Theme

    Start with a theme related to human-AI entanglement. For example: “What does education look like when every student has a personal AI mentor?” or “How does public trust function in a world where most decisions are made by predictive algorithms?” Let the AI assist in mapping out implications of this theme across different domains: work, identity, justice, ecology, etc.

  2. Build Context with a World-Building GPT

    Use your custom GPT to flesh out the world. Ask it to describe how government, infrastructure, and culture respond to the dominant technology. Example: “Describe a mid-sized North American city in 2040 where all public services are run by decentralized AI systems.” Build a document summarizing your world’s social structures, economic tensions, and cultural expressions.

  3. Visualize Spaces of Human-Machine Interaction

    Use an AI image generator to visualize key environments. Instead of fantasy cities, prompt scenes like: “A community-run AI health clinic with augmented reality interfaces,” or “An underground library where humans preserve analog media.” Use these visuals to refine your written world and vice versa.

  4. Create Agents and Ethical Tensions

    Develop characters whose roles intersect with the world’s AI systems. A teacher resisting algorithmic oversight? A technician who hacks AI to serve underrepresented communities? Write vignettes placing these characters in situations of moral or systemic ambiguity. This makes the world feel alive and contested.

  5. Use Meta-Prompting to Simulate Change

    Use recursive prompts to model how events evolve over time. Ask: “What happens when the city's predictive policing system is hacked?” or “How does a protest movement against AI governance spread?” Let the AI help simulate unfolding consequences across social, technical, and political dimensions.

  6. Reflect and Interrogate

    Pause to reflect. What does this world reveal about our current trajectory? What futures feel desirable, dystopian, or ambiguous? Use the AI to analyze recurring themes and tensions, or to suggest missing perspectives and counter-narratives.

  7. Present the World as a Critical Artifact

    Present your world as a speculative case study, design fiction, or immersive experience. Use text, visuals, and narrative to show both the seductive and the troubling aspects of this future. Emphasize your creative decisions and how AI helped challenge or expand your thinking.

This exercise develops critical and creative fluency with AI as a thinking partner. It emphasizes not only invention, but responsibility—encouraging you to design futures that reflect human complexity, systemic awareness, and ethical depth.

7. Discussion Questions

8. Bibliography

Dynamic AI Co-Creation: A Human-Centered Approach
by Will Luers | Sept. 2024