What identity means
A Finn has two layers of identity. The first is administrative: the name, use case, and icon you use to find the agent in your dashboard. The caller never encounters any of it. The second is the identity text, which is the opening block of the prompt the model acts from. That one the caller hears in every sentence.
In the editor (Start from scratch, or Edit on an existing Finn), name, voice and language are under Call flow → Identity, the time zone is Current time awareness on the Call setup tab, and identity text goes at the top of the System prompt. When you build from a playbook instead, name, icon and time zone are on the setup's Profile & knowledge tab, voice and language on Voice & call behavior, and identity text is the Role & identity field on the personality step. You can also set name, use_case and identity_text through the API. See api-finns.
The administrative fields
| Field | Where in the editor | What it controls | Caller-visible |
|---|---|---|---|
| Name | Call flow → Identity → Finn agent name | Label in the dashboard and Finn lists | No |
| Voice | Call flow → Identity → Voice persona | Which TTS voice speaks. See voice | Yes |
| Language | Call flow → Identity → Default language | Speech recognition, transcript output, TTS voice constraints | Yes |
| Time Zone | Call setup → Current time awareness | The Finn's reference time zone | No |
| Use Case | No selector. Set by the template you start from, or use_case in the API | A high-level category label | No |
| Finn Icon | Only in the playbook setup, on Profile & knowledge | Avatar in dashboard lists. Cosmetic | No |
| Identity Text | Top of the System prompt (Role & identity in the playbook setup) | Who the agent is, in the model's own instructions | Yes |
Name
Pick something you can find later. Inbound — Demo Booking and Outbound — Renewal Reminder beat Finn 1 and test copy 2. Once you have twenty agents and each one has three deployments, a name that only describes the channel is not enough to identify anything.
Use Case
A high-level category: sales, support, scheduling, surveys. There is no selector for it in the dashboard. It comes from the template you start from, or from the use_case field when you create a Finn through the API. It is not a routing decision.
Time Zone
Set this to where your callers live, not where you sit. It is the Finn's reference time zone, shown in the builder's Call setup tab as Current time awareness.
Language
This drives speech recognition, transcript output, and which voices are available. Pick the language your audience actually speaks rather than the language on your marketing site. If your callers switch languages mid-call, see multilingual before setting this.
Identity text
Identity text is the first thing in the prompt. It anchors four things: a name, a role, an employer, and a tone.
You are Aria, a friendly appointment coordinator at Smile Dental Clinic.
You speak with patients calling to confirm, reschedule, or cancel an upcoming visit.
You are warm, brief, and never push extra services.
Three lines. That is the target length. Identity text is not the place for company history, product catalogs, or a list of every question the agent might face. Facts belong in the knowledge base. Rules belong in Style and Guardrails, covered in guardrails.
Why length matters here specifically
Identity text sits at the front of every prompt on every turn. A multi-paragraph identity bloats the first token and slows the response, and the effect compounds across a whole call. Beyond that, a long identity dilutes itself. When you write eight paragraphs about who the agent is, no single sentence carries weight, and the model averages across all of it.
What vague identity does
"You are a helpful assistant for our company" produces an agent that will answer to any name, claim any role, and adopt whatever tone the caller sets. If a caller asks "who am I speaking to," the model improvises. If a caller pushes, the model drifts. Specific identity is what the model falls back on when the conversation goes somewhere the rules did not anticipate.
Give it a concrete tone instead of an adjective like "helpful." Three tone words work: warm, brief, never pushy. "Be professional" means nothing the model can act on.
Disclosure
If your agent may be asked whether it is human, put the answer in identity text or guardrails rather than leaving it to the model. A worked example:
If asked whether you are a real person, say honestly:
"I'm Aria, a voice assistant for Smile Dental."
Disclosure requirements vary by jurisdiction and by whether the call is recorded. See recording consent and compliance.
Editing later
Every field on this page is editable. Sidebar → Voice AI Agents → click the Finn → Edit. Changes apply to new calls only. Calls already in progress finish under the configuration they started with, so a bad identity edit will not stop mid-call but will affect everything dialed after you save.
There is no configuration history or rollback. Copy the current text somewhere before a significant edit, or duplicate the Finn and test the copy.
Next
- Prompting — the goal, rules, and examples that follow identity text.
- Guardrails — what the agent must never say or do.
- Voice — picking a voice that matches the identity you wrote.
- Testing — check the identity holds under a hostile or confused caller.