Home / Glossary / Persona

Concept

Persona

The identity and personality definition that controls how your AI companion behaves: the foundation of every other quality metric.

A persona is the set of instructions that tells the language model who it's pretending to be. In AI companion apps this usually includes a name, age, role, personality traits, voice, values, and dislikes. Everything downstream (how the character speaks, what they remember about themselves, whether they feel consistent across sessions) is built on top of this definition.

Most apps give you a persona builder with sliders or multi-select options. Some (Secret Desires, DreamGF) give you granular control. Some (CrushOn, GirlfriendGPT, Janitor) let you browse community-created personas instead. Janitor in particular uses the concept of "character cards": standalone persona files you can import or export.

Good personas are specific and contradictory. Generic ones produce generic output. A persona that says "sassy 22-year-old barista who collects vinyl and secretly writes poetry she never shows anyone" will produce far more interesting chat than "flirty and fun".

Most user disappointment with AI companion apps traces back to a weak persona. The model is doing what it was told; what it was told was bland.

Prompts that use this concept

Character Design

The three-sentence persona

Short personas force specificity. Three sentences about six axes (name, age, role, quirk, voice, values) is enough for an LLM to extrapolate consistently and not enough to create contradictions. Longer personas contradict themselves; this one can't.

Character Design

Contradiction persona

Characters without contradictions feel like archetypes. Every good fictional character has a public/private tension. Asking the model to simulate one forces more nuanced behavior.

Character Design

Backstory through the wound

Character cards full of lore overwhelm the model's attention budget. A single unnamed wound tied to a concrete trigger is what screenwriters call a 'ghost': it drives behavior without being stated. The model will mirror the pattern because it recognizes it from narrative training data.

Character Design

Relationship-dynamic-first persona

On Janitor/SillyTavern cards, the dynamic-with-user field predicts quality more than personality traits. LLMs trained on dialogue are better at modeling relationships than modeling people. Anchoring the character through a specific user-relationship produces more consistent voice than listing traits.

Character Design

Unreliable-narrator persona

Most personas are self-aware, which reads flat. Instructing the model to maintain a gap between stated self-knowledge and behavior produces the subtext that makes literary characters feel real. Works best on models with strong narrative priors (GPT-based, Claude-based, Mixtral tunes).

Character Design

Three-likes, three-hates, one-secret

The SillyTavern character-card community converged on this format because it gives the model six consistent hooks for flavoring dialogue plus one narrative payoff. Specific likes ('cold diner coffee', not 'coffee') generate reference-able content; generic likes don't.

Related concepts

Voice Roleplay framing

Put this into practice

Our prompt library shows these techniques in real, copy-ready prompts, tested across 22 AI companion apps.

Browse prompts →