Pullkin

The description states that Pullkin is a physics puzzle game where players launch creatures into levels filled with fragile structures, invisible forces, and predators. Players use projectiles to manipulate the environment and free trapped creatures. It includes:

• A slingshot-style interface
• Procedurally generated levels
• Deterministic physics simulation, modeled using Hooke’s law ($F = -kx$)
• A card draft system that introduces new tools per level
• A silent, hundred-level comic to guide storytelling

The game is described as being built with AI tools like ChatGPT and Codex, and the codebase was initially a 4,400-line HTML file before being modularized.

Claim: The product is a puzzle game combining physics and logic.

Evidence: Author’s own write-up.

The author states that the goal was to create a game that is:

• Simple to understand but deep enough to engage adults
• Family-friendly, with no menus or explanations needed
• A blend of immediate fun and replayability

They also report two key lessons from development:

1. Making physics predictable and trustworthy was more difficult than adding complexity.
2. AI tools helped accelerate code development, but human direction remained essential for art.

Claim: The positioning is family-friendly, logic-based puzzle with physics mechanics.

Evidence: Author’s own write-up.

The description states that the game was designed to be enjoyed by the whole family, with a focus on:

• Simplicity for children
• Depth for adults
• No written instructions or menus

It is implied that the target audience includes families and casual gamers interested in puzzle games.

Claim: The ICP is family-oriented, casual puzzle gamers.

Evidence: Author’s own write-up.

There is no evidence of a business model or pricing strategy. The description does not mention monetization, subscriptions, in-app purchases, or any commercial structure.

Claim: No business model or pricing data provided.

Evidence: Not evidenced.

The project was built using:

• AI tools: ChatGPT, Codex, GPT-5.6
• Frontend tech stack: HTML5, CSS, JavaScript, TypeScript, Three.js, WebGL, Web Workers, Web Audio API
• Backend tech stack: Node.js, Firebase
• Development process:
  • Original version: single 4,400-line HTML file
  • Rebuilt into modular architecture
  • Golden-master tests for physics determinism
  • Procedural level generation with verification via headless simulation and lightweight solver

Claim: The game uses AI-assisted development and deterministic physics.

Evidence: Author’s own write-up.

There is no evidence of traction, revenue, or user adoption. The project was submitted to a hackathon and has not been publicly released beyond that context.

Claim: No traction or maturity data provided.

Evidence: Not evidenced.

The description does not mention any competitors or market positioning relative to other puzzle games or physics-based games.

Claim: No competitive analysis provided.

Evidence: Not evidenced.

• The project is self-reported and unverified; no third-party validation of claims.
• No evidence of commercial viability, monetization, or user engagement.
• The game was built by a single developer (1 person team), which may signal scalability concerns.
• Heavy reliance on AI tools for development raises questions about long-term maintainability and intellectual property.
• The lack of revenue or customer data makes it difficult to assess product-market fit.

Inference: Lack of traction and commercial structure suggests early-stage, non-commercial project.

Evidence: Author’s own write-up.

1. Has the game been released publicly beyond the hackathon?
2. Are there any plans for monetization or user engagement metrics?
3. What is the long-term vision for the product and team expansion?
4. How does the deterministic physics model scale to more complex gameplay?
5. What are the risks of relying on AI tools for development, especially in terms of maintainability and control?