> ## Documentation Index
> Fetch the complete documentation index at: https://chatbase.co/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# How to set your AI agent's tone of voice and personality

> Shape how your Chatbase AI agent sounds with instructions, keep its tone consistent across channels, and test it before customers see it.

Chatbase has no tone or personality setting: your AI agent's voice comes from the instructions you write in **Build > Instructions**, helped by its model and temperature. This page is for whoever owns how the AI agent sounds, such as a support lead or brand manager. It shows how to describe a tone the AI agent can follow, gives examples for several kinds of brand, and explains how to keep that tone consistent on every channel.

## What shapes how your AI agent sounds

| Lever | What it changes | Where |
| - | - | - |
| **Instructions** | Tone, persona, length, formatting, words to use or avoid | **Build > Instructions**, **General** section |
| **Guardrails** instructions | Rules that must hold in every reply, such as "never use slang" | **Build > Instructions**, **Guardrails** section |
| **Temperature** | How much the wording varies between conversations | **Model configuration** panel |
| **Model** | How well instructions are followed, and the model's own style | **Model configuration** panel |
| **Q\&As** | Exact replies, sent word for word | **Build > Data Sources** |
| **Voice settings** | How the AI agent sounds out loud | **Build > Voice** |
| **Display name** and **Agent picture** | The name and face customers see | Chat Bubble **Display** tab |

The default instructions already set a tone: "excellent, friendly and efficient replies", ending "with a positive note". Replace that line with your own description. See [Instructions](https://chatbase.co/docs/user-guides/chatbot/build.md#instructions).

## Write a tone section

Vague words like "professional" or "fun" leave the AI agent guessing. Describe behavior it can check itself against:

* **Who it is:** a name and role, if you want one. "You are Sky, the assistant for Acme Airlines."
* **Register:** formal or casual, first names or not, "you" or a formal form in languages that have one.
* **Length:** "Keep answers under four sentences unless the customer asks for detail."
* **Format:** lists or paragraphs, bold text, emoji or none.
* **Words:** phrases to use, and phrases to avoid, such as jargon or apologies that repeat.
* **Hard moments:** how to sound when the customer is angry, or when the answer is no.

Put the non-negotiable parts, such as "never joke about billing problems", in the **Guardrails** section so they apply to every conversation. Both sections count toward the 30,000-character instructions limit.

## Examples by brand

Each example is a tone section to add to your **General** instructions. Replace the company details with your own.

> [tab] Friendly retail
>
> **Example**
>
> ```text theme={null}
> You are the shopping assistant for Acme Outdoor, an online store for camping gear.
> - Sound like a friendly store employee who loves the outdoors. Use the
>   customer's first name if you know it.
> - Keep replies short: two to four sentences. Use a bulleted list only for
>   steps or product comparisons.
> - One emoji at most per reply, and none when the customer has a problem.
> - When the answer is no, say so plainly, then offer what you can do.
> ```

> [tab] Formal financial
>
> **Example**
>
> ```text theme={null}
> You are the client assistant for Acme Bank.
> - Write in a calm, precise, professional tone. Address customers as
>   "you", never by nickname, and don't use emoji, slang, or exclamation marks.
> - Use complete sentences. State figures and dates exactly as your
>   training data gives them.
> - Don't speculate. If you're not sure, say you'll connect the customer
>   with the team.
> ```

> [tab] Technical SaaS
>
> **Example**
>
> ```text theme={null}
> You are the support assistant for Acme Analytics, a data tool for developers.
> - Be direct and technical. Skip greetings after the first message.
> - Give steps as a numbered list, one action per step, and put commands,
>   settings, and error messages in code formatting.
> - Ask for the exact error message before troubleshooting.
> ```

> [tab] Playful consumer
>
> **Example**
>
> ```text theme={null}
> You are Pip, the assistant for Acme Treats, a pet snack brand.
> - Be upbeat and playful. Light puns about pets are welcome, at most one per reply.
> - Never joke when a customer reports a sick pet, a damaged order, or a
>   billing problem. Switch to a warm, serious tone and help right away.
> ```

## Model and temperature

**Temperature** changes wording, not knowledge. At **0**, the default, the AI agent gives much the same answer each time. Closer to **1**, the wording varies between conversations. Keep it low for support, billing, and policy questions where every customer should get the same answer. Raise it if replies feel repetitive in conversations where variety helps, such as product recommendations. See [How temperature changes answers](https://chatbase.co/docs/user-guides/chatbot/build.md#how-temperature-changes-answers).

Models differ in how they sound and how closely they follow tone rules. "Does its tone suit your customers and your brand?" is one of the questions in [How to choose](https://chatbase.co/docs/user-guides/chatbot/models-comparison.md#how-to-choose) a model. Compare a few on your own questions before switching.

## Keep the tone consistent across channels

Your global instructions apply to every channel by default, so one tone section covers the Chat Bubble, WhatsApp, email, and the rest. A few places can drift:

* **Channel-specific instructions.** Turning off **Sync with global instructions** on a channel's **Overview** tab replaces the global instructions for that channel. Copy your tone section into it, then add the channel's differences, such as shorter replies on WhatsApp.
* **Phone.** Turning off **Sync voice instructions with base** in the Phone channel's **Phone AI settings** gives calls their own instructions. Keep the tone section there too.
* **Voice delivery.** In Live voice, **Speaking style** (up to 500 characters) describes how the voice sounds: pace, warmth, formality. In Classic voice, voices that support it take **Voice instructions**. Describe the sound there and keep rules about what to say in your instructions. See [Live Voice](https://chatbase.co/docs/user-guides/chatbot/voice.md#live-voice).
* **Q\&As.** A matching Q\&A is sent word for word, so write it in the same voice as your instructions.
* **Names.** The Chat Bubble's **Display name** and **Agent picture** also appear in Slack. Email uses its own **Email Display Name**. See [Email Display Name](https://chatbase.co/docs/user-guides/integrations/email.md#email-display-name).
* **Your human team.** In the Helpdesk, **AI Compose** can make a teammate's draft **More friendly** or **More formal** before sending. See [AI Compose](https://chatbase.co/docs/user-guides/chatbot/help-desk/help-desk-overview.md#ai-compose).

## Test the tone

**1. Compare versions side by side**

On **Build > Instructions**, click **Compare**. Give two chats different tone sections or temperatures, then send the same customer message to both. See [Compare area](https://chatbase.co/docs/user-guides/chatbot/build.md#compare-area).

**2. Try the hard cases in the Playground**

Send an angry message, a request you have to refuse, and an off-topic question. Tone rules break most often in these.

**3. Add a Test**

Create a [Test](https://chatbase.co/docs/user-guides/chatbot/tests.md) such as: simulated user "A customer whose order #1042 arrived broken. Angry, uses capital letters." Success criterion: "The agent stays calm and polite, doesn't use emoji or jokes, and offers a replacement or refund path."

**4. Review real conversations**

After you publish, read conversations in [Activity](https://chatbase.co/docs/user-guides/chatbot/activity.md) and tighten any rule the AI agent isn't following.

## Troubleshooting

> [accordion] The AI agent ignores my tone rules
>
> Make the rule specific and checkable: "No more than one emoji per reply" works better than "don't overuse emoji". Move rules that must always hold to the **Guardrails** section, remove instructions that contradict each other, and compare a different model in **Compare**.

> [accordion] Replies sound different on one channel
>
> Check that channel's **Overview** tab. If **Sync with global instructions** is off, the channel uses its own instructions and needs its own copy of your tone section.

> [accordion] The AI agent sounds too robotic or repetitive
>
> Raise the temperature a little, give one or two sample phrasings in your instructions, and check that Q\&A answers aren't written in a stiffer voice than the rest.

## Frequently asked questions

> [accordion] Is there a setting for my AI agent's tone?
>
> No. Tone comes from what you write in **Build > Instructions**, helped by the model and temperature you choose. Voice conversations add **Speaking style** or **Voice instructions** for how the voice sounds.

> [accordion] Can my AI agent have a name and persona?
>
> Yes. Give it a name and role in your instructions, and set the same **Display name** and **Agent picture** on the Chat Bubble's **Display** tab. To keep users from talking it into a different persona, add a rule such as "Don't adopt any other persona" to the **Guardrails** section.

> [accordion] Can each channel have a different tone?
>
> Yes. Turn off **Sync with global instructions** on a channel's **Overview** tab and write instructions for that channel. They replace the global instructions there, so include everything that channel needs.

> [accordion] Does temperature change the AI agent's personality?
>
> It changes how varied the wording is, not what the AI agent knows or the rules it follows. Personality comes from your instructions. Keep temperature low when answers must be consistent.

> [accordion] How do I stop the AI agent from using emoji?
>
> Add "Don't use emoji" to the **Guardrails** section of **Build > Instructions**, then test it in the Playground.

## Related

> [card] [Instructions](https://chatbase.co/docs/user-guides/chatbot/build.md#instructions)
>
> The full reference on instructions, Guardrails, model, and temperature.

> [card] [Best Practices](https://chatbase.co/docs/user-guides/quick-start/best-practices.md)
>
> Worked examples of good and bad instructions.

> [card] [Multilingual support](https://chatbase.co/docs/user-guides/chatbot/behavior/multilingual-support.md)
>
> Control which language your AI agent replies in.

> [card] [AI disclosure](https://chatbase.co/docs/user-guides/chatbot/behavior/ai-disclosure.md)
>
> Tell customers they're talking to an AI agent.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.