WeBattle

Generates multi-turn interactive narratives by chaining LLM prompts that maintain story context across player choices. The system accepts natural language game premises and player inputs, then uses prompt engineering to generate contextually-aware story branches that respond to player decisions. Each turn maintains conversation history to preserve narrative continuity, though coherence degrades with longer play sessions due to context window limitations and accumulated prompt drift.

Provides a web-based UI that accepts natural language descriptions of game concepts and automatically scaffolds playable games without requiring code. Users describe game themes, tone, character archetypes, and win/loss conditions in plain text, which the system parses and translates into LLM prompts and game loop configurations. The interface abstracts away API management, prompt engineering, and game state handling, presenting a simple form-based or conversational setup flow.

Converts game definitions into executable game instances that manage turn-based gameplay loops, maintain game state across player interactions, and render narrative content and choice options in a web interface. The system handles session management, API call orchestration to the underlying LLM, and presentation of generated story content and player choices. Each game instance maintains a session ID, conversation history, and game-specific metadata (creator, title, play count) in a backend store.

Generates shareable URLs for created games that allow any user to play without requiring authentication or special permissions. Games are assigned unique identifiers and published to a public or semi-public registry, enabling discovery through direct links, social sharing, or platform-wide game listings. The system tracks play counts, player feedback, and game metadata to support community features like ratings or featured game curation.

Implements a two-tier pricing model where free users can create and play games with basic features (limited API calls per month, standard LLM models, basic analytics), while premium subscribers unlock higher quotas, advanced LLM models, custom branding, and detailed game analytics. The system enforces usage limits through API call tracking, session quotas, and feature flags that enable/disable functionality based on subscription status.

Abstracts underlying LLM provider details (OpenAI, Anthropic, or equivalent) behind a unified interface, allowing games to run on different models without code changes. The system likely maintains provider-specific prompt formatting, token counting, and API call handling, with a configuration layer that selects the active provider based on subscription tier or user preference. This enables cost optimization (cheaper models for free tier, premium models for paid users) and resilience through provider fallback.

Maintains a searchable index of created games with metadata (title, description, creator, creation date, play count, ratings) that enables discovery through browsing, search, or algorithmic recommendations. The system likely stores game metadata in a database with full-text search capabilities, and may implement ranking algorithms that surface popular or highly-rated games. This supports community engagement by helping players discover games beyond direct sharing.

Stores game session state (conversation history, player choices, game progress, turn count) in a backend database, enabling players to resume games across browser sessions or devices. The system assigns session IDs to each game instance, maintains conversation history for context window management, and may implement auto-save functionality to prevent progress loss. Session recovery likely requires authentication or session token validation to prevent unauthorized access to other players' games.