Inworld AI

What is Inworld AI?

Inworld AI is a platform that provides game developers with AI characters designed specifically for games. The characters are built using natural language processing, machine vision, and speech-to-text, with the goal of making them act and interact like real people. Key features include real-time generative AI, a character engine that makes AI expressive and multimodal, and a “contextual mesh” that keeps characters consistent with your game’s world or brand. APIs are available to simplify integration.

The Inworld engine is a collection of machine learning and character AI models designed to mimic human gestures, speech, emotions, and memory while maintaining safety. It enables AI NPCs with more advanced thinking, perception, and behavior than traditional NPCs. These are “agentic AI” characters that can actively guide, challenge, or entertain players. Inworld’s stated aims are to boost player engagement, increase revenue, and improve core gameplay loops.

Who created Inworld AI?

Inworld AI was founded by Kylan Gibbs (CEO and Co-Founder), Ilya Gelfenbeyn (Executive Chairman and CSO), and Michael Ermolenko (CTO and Co-Founder). The team has a background in conversational AI and generative models, with a track record of launching ventures in the AI industry.

What is Inworld AI used for?

• Powering gameplay: Bring experiences to life with AI-driven characters.
• Streamlining development: Boost productivity with AI-generated game assets.
• New gameplay mechanics: Deliver fresh ways to play using AI logic engines.
• Deeper player connections: Create meaningful interactions, including NEO NPCs for emergent storytelling.
• Real-time adaptation: Mechanics that change based on player decisions, with characters reacting to player input for personalized gameplay.
• Beyond NPCs: Use agentic AI for autonomous companions or intelligent crowds.
• LiveOps support: Manage player experiences as content evolves.
• Creative assistance: Use AI-assistive features for game narratives, dialogue, and voices.
• Agent training: Fine-tune AI agents using annotations, reinforcement learning, and log reviews to match your game’s lore and preferences.
• Evolving worlds: Build worlds that change as players interact with them.
• Player behavior analysis: Understand players to personalize their experience.
• AI infrastructure: Establish a durable AI foundation for long-term development.