> ## Documentation Index > Fetch the complete documentation index at: https://invoca-5bd45748-mintlify-17ed87db.mintlify.site/llms.txt > Use this file to discover all available pages before exploring further. # Identifiers: Personality > Tone and voice register when the system talks, as distinct from when it just renders data. **No verbal register has been decided for any Invoca agentic feature yet.** This page proposes a framework for making that decision — it is not the decision itself. See [Coverage, stated honestly](/invoca-design-system/ai-experience/overview#coverage-stated-honestly). ## What it governs The tone and register of sentences an AI feature *produces* — a generated summary, an explanation, a hedge, a refusal — as distinct from data it merely *renders*, like a chart or a table of call metrics. It governs how "talking" content should sound; it does not govern whether uncertainty is disclosed at all (that is [Trust builders](/invoca-design-system/ai-experience/trust-builders/caveat)) or what the feature is named (that is [Identifiers: Name](/invoca-design-system/ai-experience/identifiers/name)). It does not govern [Content: Voice and tone](/invoca-design-system/content/voice-and-tone) itself — Invoca's general brand voice, which this page inherits and narrows for AI-generated language specifically. ## Vocabulary | Term | Means | | --------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Voice** | Invoca's three stated brand traits — Empowering, Eye-opening, Bold — from [Content: Voice and tone](/invoca-design-system/content/voice-and-tone) | | **Tone** | How those traits flex moment to moment — more measured when the system is uncertain, more direct when it is confident | | **Personality** | This page's umbrella term for deciding how "human" an AI feature's sentences should sound — a decision, unlike a static UI label, that has to hold across an unbounded range of generated text | **"Talking" is not "rendering."** A generated summary sentence is talking, and in scope here. A table of call metrics beside it is rendering, and out of scope — it is governed by [Foundations: Typography](/invoca-design-system/foundations/typography) and the relevant component, not by this page. ## Choosing a value | If you need to… | Use | Not this, because | | ----------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------ | | Make AI-generated sentences sound like Invoca | Invoca's existing three brand traits from [Content: Voice and tone](/invoca-design-system/content/voice-and-tone) | Inventing a separate, "chattier" personality for AI surfaces — that splits the brand exactly at the moment a user first notices something is different | | Have the AI hedge when it's not sure | Write the hedge in this page's register; decide *whether* to show one at all in [Trust builders](/invoca-design-system/ai-experience/trust-builders/caveat) | Deciding here whether uncertainty gets disclosed — that is a different page's job | | Have the AI apologize for an error or a refusal | A brief, single acknowledgment, per `TITAN-VOICE-03`'s concise-over-exhaustive rule | An effusive, repeated apology that reads as performance rather than information, and buries what the user actually needs — what to do next | | Make the AI sound casual or friendly, like a chat companion | Hold it to Bold — clear and direct — from Invoca's existing traits | Adding warmth as a new, undecided fourth trait the brand has not signed off on | ## Reference Nothing is decided. No Invoca agentic feature has a stated tone or register today, including Signal AI's shipped transcript summaries. This section will be generated from a real decision once one exists. ## Relationships Personality directly inherits [Content: Voice and tone](/invoca-design-system/content/voice-and-tone)'s three traits and its constraints — `TITAN-VOICE-01` (plain language over technical wording), `TITAN-VOICE-02` (no acronyms or insider phrasing), `TITAN-VOICE-03` (concise over exhaustive) — all apply to AI-generated sentences exactly as written for the rest of the product; this page does not restate them, it narrows their application. It pairs with [Identifiers: Name](/invoca-design-system/ai-experience/identifiers/name) — a feature's name and its speaking register are usually decided together — and with the overview's disclosure requirement: tone must never obscure the six disclosure-and-recourse questions. ## Accessibility * Plain language (`TITAN-VOICE-01`) doubles as an accessibility aid: it helps readers with cognitive or language-processing differences as much as it helps a reader outside the company understand copy without translation. * Tone must never substitute for or obscure the six disclosure-and-recourse answers from the [overview](/invoca-design-system/ai-experience/overview#disclosure-recourse) — what the system used, how sure it is, how to check it, how to correct it, and how to get out. A warm register that omits or buries any of these is not a tone problem; it is a missing answer wearing a friendly voice. ## Constraints | ID | Constraint | Rationale | | -------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **TITAN-PERSONA-01** | AI-generated sentences follow Invoca's three brand voice traits — Empowering, Eye-opening, Bold. No separate "AI voice" is introduced. | A second voice for AI content splits the brand exactly where consistency matters most: the moment a user notices the product is talking differently. | | **TITAN-PERSONA-02** | Tone never substitutes for the six disclosure-and-recourse answers from the overview. A friendly register is not a stand-in for saying what the system used or how sure it is. | Warmth and disclosure are different axes. Optimizing one at the other's expense is how "confident and wrong" becomes "confident, charming, and wrong." | | **TITAN-PERSONA-03** | Hedging and refusal language stays concise, per `TITAN-VOICE-03` — no more than one brief acknowledgment before the substantive content. | Exhaustive apology reads as performance and pushes the actually useful information — what to do next — further down the response. | | **TITAN-PERSONA-04** | Personality is decided for talking content only. Rendered data — tables, charts, transcript excerpts — carries no personality treatment. | Keeps this page's scope from creeping into typography or component pages already governed elsewhere. | | **TITAN-PERSONA-05** | No AI-specific personality trait is added beyond Invoca's existing three without a stated brand-level decision. | Mirrors `TITAN-COLOR-05`'s four-statuses logic: an ungoverned addition here is exactly how "helpful," "witty," and "empathetic" pile up with nothing distinguishing them. | ## Divergences Not applicable. Nothing is shipped yet to diverge from. ## Gaps * Whether tone should shift by outcome state — more measured when uncertain, more direct when confident — is undecided. * Whether personality is one voice for all of Invoca's agentic surfaces or decided per feature is the same per-feature-or-once question flagged on the [overview](/invoca-design-system/ai-experience/overview#gaps). * How Invoca's three brand traits actually read once generated by a model, rather than written by a copywriter, has not been evaluated. ## Related [Identifiers: Avatar](/invoca-design-system/ai-experience/identifiers/avatar) · [Identifiers: Color](/invoca-design-system/ai-experience/identifiers/color) · [Identifiers: Iconography](/invoca-design-system/ai-experience/identifiers/iconography) · [Identifiers: Name](/invoca-design-system/ai-experience/identifiers/name) · [AI Experience overview](/invoca-design-system/ai-experience/overview) · [Content: Voice and tone](/invoca-design-system/content/voice-and-tone) ## Why it works this way Restricting personality to Invoca's existing three brand traits, rather than letting AI surfaces develop their own, keeps the brand from fracturing at its most visible new surface. A model's output is the first place many users will notice the product doing something new; if it also sounds like a different product at that moment, the inconsistency compounds instead of canceling out. Scoping this page to "talking," not "rendering," keeps it from re-deciding typography or component rules that already govern how data displays. A generated sentence needs a tone decision because its exact words are new every time; a rendered number does not, because its presentation was already decided elsewhere.