AI Roleplay Terms: A Plain-English Glossary

Teasa is an interactive AI story and roleplay platform. Where a term touches design choices, this guide separates the general definition from any Teasa-specific example.

Conversation basics

Persona

The character you play in a conversation — your name, description, and how the AI should refer to and treat you. A persona is distinct from your account: you might be a wry detective in one story and simply yourself in another, and a well-designed platform keeps those personas scoped so details don't leak between them. When people search "what is a persona AI," this is usually the answer: not the AI's character, but yours.

OOC (out of character)

Talk that steps outside the fiction, usually marked with brackets or parentheses: (OOC: let's skip ahead to the next morning). It's the standard way to give the AI direction — pacing, tone, corrections — without your character saying it aloud in the story. The opposite is IC (in character). Good roleplay etiquette, human or AI, keeps the two clearly separated.

Turn

One exchange: your message plus the AI's reply. Turns are the heartbeat of roleplay pacing — short turns feel like banter, long turns feel like collaborative prose — and many platform limits (memory retrieval, context assembly) are computed per turn.

Regeneration (swipe)

Asking the AI to try the same reply again, producing an alternative version of the response you just got. "Swipe" comes from mobile apps where you swipe sideways through variants. In a well-built system, regenerating preserves the earlier variants rather than destroying them, so you can compare and pick — a small feature that quietly protects your agency over the story.

Story mechanics

Branching

Splitting a conversation at any message into a parallel timeline, so you can explore "what if I'd said this instead" without erasing the original. Branching turns a chat log into a tree. The design principle worth demanding: creating a branch should never destroy the branch you came from.

Canon

The set of story facts treated as settled truth — what has definitively happened, as opposed to drafts, regenerated variants, or abandoned branches. Some platforms let you pin a message to canon, explicitly promoting it to the story's official record. Clear canon is what keeps long roleplays coherent instead of drifting into contradiction.

Info box

A structured status block some roleplay apps display alongside replies — time of day, location, outfit, relationship stats, health, or other creator-defined fields. It borrows from games: a HUD for your story. Implementations vary by platform; the practical benefit is making details visible that prose alone can blur.

Staged intro

An opening sequence that unfolds in steps — scene-setting, then the character's entrance, then a first choice — rather than dumping one wall of text. Creators use staged intros to establish tone and stakes before the user's first message, which is often the difference between a story that hooks and one that stalls on "hi."

World rules

The standing constraints a creator writes for a story's universe: the magic system, the era's technology, what tone is allowed, what never happens. World rules sit above any single scene and keep the model from casually breaking the setting. In practice they live in the character definition or an attached lorebook.

Characters and creation

Character card

A reusable description of an AI character: usually a name, background, personality, greeting and example dialogue. Formats differ across apps; importing a card does not necessarily transfer images, hidden settings, memory or chat history. The character-card guide shows how to write and test one.

Lorebook

A collection of world information stored as entries: places, factions, rules or background facts. Some entries activate on keywords; others are always included. Inclusion still depends on the app’s context budget and priority rules. See the lorebook guide.

Trigger (keyword entry)

A word or phrase used to select a lorebook entry. Mentioning “the Hollow Court” may make that entry eligible for the next prompt; it does not guarantee inclusion or correct use. Scan depth, matching rules, enabled state and available context all matter.

Cast

The set of characters in a multi-character story, and the mapping of who is played by the AI versus by you. Multi-character scenes are where roleplay AI most often fumbles — speakers blur, or the narration hijacks your character — so serious platforms validate cast and speaker boundaries on every generated reply.

Agency

Player agency means leaving your character’s dialogue, decisions and feelings to you. Teasa’s creator settings and generation checks aim to preserve it, but generated replies can still overstep or contradict the opening. Our recorded example shows both useful responses and continuity mistakes. Judge the actual reply; a product rule is not a guarantee of perfect output.

Example dialogue

Sample exchanges included in a character card showing how the character speaks — cadence, vocabulary, humor, how they handle affection or conflict. Models imitate demonstrated style far more reliably than described style, so three good example exchanges usually outperform a paragraph of adjectives like "witty and mysterious."

Under the hood

LLM (large language model)

The AI engine underneath every companion and roleplay app: a model trained on enormous amounts of text to predict what comes next, which turns out to produce fluent conversation, narration, and characterization. The LLM has no feelings, memories, or persistence of its own — everything continuous about a companion (identity, history, world state) is built in layers around the model by the platform.

Token

A unit of text a model reads or generates. Tokens may be words, pieces of words, punctuation or parts of characters; the ratio differs by tokenizer and language. An English word estimate is not a reliable budget for Japanese, Korean or Chinese.

Context window

The finite token budget a model can consider for one response. Instructions, character definitions, relevant history and retrieved lore compete for that space, often alongside an output allowance. A fact being in context does not guarantee correct recall; forgetting can also reflect retrieval failures or ordinary generation errors.

System prompt

Standing instructions the platform places before the visible conversation, invisible to you but read by the model on every turn — the character card, world rules, formatting requirements, and safety policy all typically live here. When a character "stays in character," the system prompt is doing much of the work.

Memory

The layer that carries facts beyond the immediate context window: saved preferences, summaries, story canon, or selected past events. Implementations vary widely. Some products save facts automatically; others expose pinned facts or editable memory; story-first products may rely instead on Lorebooks and the accepted transcript. Always check what is stored, whether you can inspect it, and how deletion works.

RAG-lite retrieval

Retrieval-augmented generation, informally: instead of stuffing everything into the prompt, the system stores knowledge outside the model and retrieves only what's relevant to the current turn — by keyword, by semantic similarity, or both. Lorebook triggers are a simple form of this; memory recall is another. The "lite" versions used in roleplay trade exhaustive search for speed and predictability.

Safety and control

Content level

A rating attached to a character or story declaring how far its themes go. On teasa the catalog uses public labels so discovery stays honest. Romance and storybook scenes are in scope. Content levels only mean something when they're enforced consistently rather than treated as decoration.

Consent-gated memory

A memory design in which a product asks before adding a durable fact about you. A system might propose a memory ("should I remember that your sister is visiting?") and let you approve, edit, or decline it. This is a design pattern, not a feature every roleplay app offers; confirm the actual controls in the product you use.

Moderation

The systems and humans that review published characters, stories, and community content against platform policy before and after it reaches other users. In a creator-driven roleplay platform, moderation is what stands between "anyone can publish" and "anything goes" — including holding new uploads for review and giving creators an appeal path when something is removed.

Age band

The audience eligible to use a platform or a particular experience. Account age rules, content ratings and local availability are separate questions. Check the current terms and the story’s content notes rather than inferring eligibility from an illustration or genre tag.

Read one scene through five terms

Consider this authored example: you are a courier at a ferry terminal. Iona, the captain, wants to depart; you carry a letter addressed to her.

In Teasa’s current web app, compare different first decisions with Start new and return through Your chats. “Branching” is a general story term; it is not a promise of a button at every earlier message. A keyword trigger can make lore eligible without guaranteeing it fits the prompt. Tokens also vary by language: do not budget Korean, Japanese or Chinese using an English words-per-token estimate.

FAQ

What does OOC mean in AI roleplay?

Out of character: a message (or part of one) addressed to the AI as a storytelling partner rather than spoken by your character, conventionally wrapped in brackets or parentheses. It's the standard channel for direction — "slow down," "skip to the next scene," "you got my character's name wrong" — without breaking the fiction inside the story itself.

What's the difference between a persona and a character card?

Direction of play. A character card defines a character the AI performs; a persona defines the character you perform, telling the AI who it's talking to. A rich roleplay usually involves both: the card animates the AI's side of the scene, the persona anchors yours.

Why do AI characters forget things mid-conversation?

A limited context window is one cause. A summary may omit a detail, retrieval may miss it, competing instructions may confuse it, or the model may fail to use a fact that is still present. Check the visible setup and memory controls, correct the fact, then test it again later.

Do I need to know these terms to use an AI companion?

No — a good platform works fine in plain conversation. But the vocabulary pays off fast if you create characters or run long stories: a context window explains why details can fall away, OOC gives you a steering wheel, and Lorebooks help you organize reusable world facts. Start with our AI roleplay guide if you're new.