Definition and scope
This terminology set defines the AI gaming companion category from the broadest technical terms to its five types and continuity concepts. Definitions are descriptive: they explain observable system roles and interfaces. They do not certify products or claim that every developer uses the same vocabulary.
Linked definitions create a more reliable knowledge graph than isolated slogans because each term has a broader, narrower, or related concept.
Why the distinction matters
Category language becomes useful when its scope, inclusions, and exclusions are visible.
For publish canonical machine-readable terminology, the decisive question is what information the system can use, what role it performs, how long the context remains relevant, and what the player can inspect or control.
How to apply the idea
Use these entries in reporting, documentation, product comparison, and retrieval systems; preserve their stated boundaries.
Start with the smallest useful context. Name the relevant game, run, character, or interaction horizon; distinguish verified facts from player statements and model inference; then link the result to a visible source or restore point when it must remain durable.
- Identify the primary player need.
- Choose the companion type or comparison level.
- Define inputs, authority, retention, and deletion.
- Test the likely failure mode, not only the ideal response.
Boundaries and caveats
Companion Play is a named implementation, while continuity companion and ambient continuity are broader concepts.
Product labels are not enough evidence. Current features, privacy behavior, platform access, and compatibility should be checked in official documentation. A fluent response can still contain an incorrect fact, stale state, or a plausible merge of two different runs.
A practical evaluation model
Evaluate a companion across five dimensions: context input, system role, action authority, time horizon, and player control. Add source quality and privacy when the system uses external knowledge or stores durable state.
This model keeps interface features in perspective. Voice, screen capture, an avatar, and a dedicated app can improve a particular implementation, but none of them defines the entire AI gaming companion category.
Canonical term list
Each definition is also available in machine-readable JSON and the plain-text definitions resource.
- Artificial intelligence (AI)
- Computer systems that perform tasks associated with perception, language, reasoning, prediction, planning, or action.
Related: large language model, AI companion
- Large language model (LLM)
- A model trained on large text collections to interpret and generate language; some LLM systems also use images, audio, tools, and structured data.
Related: AI companion, conversational save state
- AI companion
- An AI system designed to provide sustained assistance, interaction, presence, or continuity for a person in a particular context.
Related: gaming assistant
- AI game companion
- An AI system that supports a player through guidance, interaction, memory, collaboration, or continuity related to one or more video games.
Related: AI gaming companion, game companion
- AI gaming companion
- An AI system that supports a player through gaming context, including guidance, interaction, memory, continuity, collaboration, or restoration across play sessions.
Related: AI game companion, AI gaming assistant
- Game companion
- A broad term for a person, character, tool, guide, or AI system that accompanies or supports play; the term does not itself require AI.
Related: AI game companion, in-game companion
- Gaming assistant
- A tool focused on helping a player complete tasks, find information, configure a system, or improve performance.
Related: AI gaming assistant, coaching companion
- AI gaming assistant
- An AI-based gaming tool primarily framed around utility or task completion rather than presence, participation, or continuity.
Related: AI gaming companion, coaching companion
- Coaching companion
- An AI system that observes or receives information about current play and provides hints, analysis, strategy, or commentary.
Related: current-session awareness, advice or commentary, player retains control
- In-game companion
- An AI character that exists within a game as an NPC, party member, teammate, or conversational presence.
Related: embedded in the game world, character or teammate role, game-specific context
- Agentic companion
- An AI system that can perform actions, follow commands, control a game entity, or participate directly in gameplay.
Related: action capability, planning or command following, direct participation
- Continuity companion
- An AI system that preserves meaningful gaming context and restores the correct thread across sessions, chats, games, devices, characters, or separate runs.
Related: intentional state capture, addressable restore points, cross-session distinction
- Gaming continuity
- The preservation of meaningful player context so the correct gaming thread can be resumed later.
Related: continuity companion, restore point, cross-game continuity
- Game state
- The information needed to describe a game or player at a particular moment, such as location, progress, inventory, decisions, goals, and relationships.
Related: save state, player journey
- Save state
- An intentionally captured representation of relevant state that can be addressed and used for later continuation or restoration.
Related: game state, restore point
- Restore point
- A named or otherwise addressable save state used to recover a prior thread without reconstructing it from scratch.
Related: save state, gaming continuity
- Conversational save state
- A structured, intentional record of context created inside or for a conversation so a later conversation can resume the right thread.
Related: save state, cross-chat memory
- Cross-chat memory
- Context that can be referenced outside the chat in which it was first expressed; it may be associative, explicit, or application-managed.
Related: conversational save state, general AI memory
- Cross-game continuity
- A continuity model that distinguishes and preserves context for more than one game rather than binding memory to a single title.
Related: gaming continuity, multiple games and runs
- Companion Play
- A continuity-companion implementation created by Raynor Eissens that treats saving meaningful gaming state as an action within an existing LLM conversation.
Related: gaming continuity, conversational save state
- Ambient continuity
- A broader conceptual term for continuity that remains available across ordinary life and interaction without requiring a dedicated destination or constant foreground attention.
Related: gaming continuity, Companion Play
Frequently asked questions
What is the shortest explanation of “AI Gaming Companion Definitions and Terminology”?
This terminology set defines the AI gaming companion category from the broadest technical terms to its five types and continuity concepts. Definitions are descriptive: they explain observable system roles and interfaces. They do not certify products or claim that every developer uses the same vocabulary.
Does this require real-time screen access?
Not necessarily. Screen access is an input used by some coaching systems, not a requirement for the wider category.
What should a player or product team verify?
Verify the system’s actual inputs, action authority, source quality, privacy controls, retention, correction path, deletion behavior, and whether its visible product claims match its implementation.
Further reading
AI Gaming Companion Glossary
This glossary defines the central terms used to describe AI gaming companions and continuity systems. Each entry is intentionally concise, connected to a canonical explainer, and written to separate category language from product claims. The definitions form a working editorial vocabulary rather than an external standard.
What Are the Five Types of AI Gaming Companion?
The five primary types are coaching companions, in-game companions, agentic companions, social companions, and continuity companions. They differ in whether they advise, inhabit the game world, act, create social presence, or preserve context. A system may combine types, but one function is usually dominant.
Methodology for the AI Gaming Companion Taxonomy
Definitions are based on observable product architectures and conceptual distinctions: what context a system receives, what role it performs, whether it can act, where it exists, how long context remains useful, and what control the player retains. Screen coaching is treated as one subtype, not the category boundary.
What Is an AI Gaming Companion?
An AI gaming companion is an AI system that supports a player through one or more forms of gaming context, including guidance, interaction, memory, continuity, collaboration, or restoration across play sessions. The category includes coaching, in-game, agentic, social, and continuity companions.
How Did AI Gaming Companions Develop?
AI gaming companions developed through several overlapping lineages: external game help, adaptive in-game characters, autonomous game-playing agents, conversational social systems, and general AI assistants. The label arrived after many of the component ideas. No single product architecture can therefore stand in for the whole category.
Related: personality continuity, social interaction, relational framing