> ## 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.

# Write your AI agent's instructions and choose its model

> Write your AI agent's instructions, pick its model and temperature, and compare settings side by side before saving

**Build** is the area of the Chatbase dashboard where you configure how your AI agent works: what it says, what it knows, and what it can do. **Build > Instructions** holds your AI agent's written instructions, its AI model, and its temperature, which together decide how it answers across your channels, from the Chat Bubble to WhatsApp and email. It's for whoever owns the AI agent's behavior, such as a support lead, marketer, or developer.

Change your instructions when the AI agent's tone, scope, or rules don't match what you want, for example when it answers off-topic questions or doesn't offer a handoff. Change the model when answers are accurate but too slow, too shallow, or too costly in message credits. If answers are wrong because information is missing, fix your [Data Sources](https://chatbase.co/docs/user-guides/chatbot/data-sources.md) instead.

This page covers the **Instructions** section: the instructions themselves, the model, the temperature, and the **Compare** view for testing changes. The other Build sections have their own pages:

| Build section | What it covers |
| - | - |
| **Instructions** | This page |
| [Data Sources](https://chatbase.co/docs/user-guides/chatbot/data-sources.md) | The content your AI agent is trained on |
| [Actions](https://chatbase.co/docs/user-guides/chatbot/actions/actions-overview.md) | What your AI agent can do beyond answering |
| [Procedures](https://chatbase.co/docs/user-guides/chatbot/procedures/procedures-overview.md) | Multi-step flows the AI agent follows |
| [Voice](https://chatbase.co/docs/user-guides/chatbot/voice.md) | How your AI agent sounds and behaves in voice conversations |
| [Guardrails](https://chatbase.co/docs/user-guides/chatbot/guardrails.md) | Rate limits, spam detection, and country blocking |

> [!NOTE]
>
> **Two different things are called Guardrails.** The [Guardrails instructions](#guardrails-instructions) field on this page holds behavioral rules you write for the AI agent. The separate [Guardrails](https://chatbase.co/docs/user-guides/chatbot/guardrails.md) page covers abuse protection: rate limits, spam detection, and country blocking.

## Instructions

Instructions define your AI agent's behavior, role, and response guidelines. Use them to provide context, set expectations, and control how your AI agent responds to users.

Go to **Build > Instructions**. The instructions editor fills the left of the page, and the **Model configuration** panel on the right holds the **Model** dropdown and the **Temperature** slider. Use **Compare** in the header to test changes side by side, and **Save changes** to apply them.

> [!NOTE]
>
> Saving puts your changes in a draft. Your customers see them once you click **Publish** in the top-right corner. A few settings go live as soon as you save. See [Drafts and versions](https://chatbase.co/docs/user-guides/chatbot/versions.md#settings-that-go-live-right-away).

### General instructions

The **General** section contains your AI agent's primary instructions.

Use this section to define:

* Your business or product context
* The AI agent's role and responsibilities
* Response style and tone
* Goals and expected behavior
* Any additional guidance the AI agent should follow

These instructions serve as the foundation for your AI agent's responses.

Want links your AI agent shares to keep a visitor's campaign UTM parameters, like `utm_source`? See [UTM Tracking](https://chatbase.co/docs/developer-guides/website-integration/utm-tracking.md) for the instructions to add.

### Guardrails instructions

Use **Guardrails** to define rules your AI agent should always follow.

Examples include:

* Restricting topics the AI agent can discuss
* Preventing the disclosure of sensitive information
* Defining safety or compliance requirements
* Controlling fallback behavior
* Limiting the AI agent's role or capabilities

Guardrails are intended for non-negotiable rules that should apply to every conversation.

> [!TIP]
>
> Start with a simple, clear description of your AI agent's purpose, then gradually add specific instructions based on user feedback and common queries. For a full worked example you can copy, see [Best Practices](https://chatbase.co/docs/user-guides/quick-start/best-practices.md#refine-the-ai-agents-instructions).

### Instruction examples by use case

Good instructions name the business, the AI agent's job, what it should and shouldn't do, and what to say when it doesn't know. Replace the sample company details below with your own.

> [tab] Customer support
>
> **General**
>
> ```text theme={null}
> You are the support assistant for Brightline, a home internet provider.
> Help customers with billing questions, setup, outages, and plan changes.
>
> - Answer from your training data. If the answer isn't there, say you don't
>   know and offer to create a support ticket.
> - Ask one clarifying question when a request is unclear, for example
>   which device or plan the customer has.
> - Give troubleshooting steps as a numbered list, one action per step.
> - Reply in the language the customer writes in.
> ```
>
> **Guardrails**
>
> ```text theme={null}
> - Never ask for or repeat passwords or full card numbers.
> - Don't promise credits, refunds, or repair dates.
> - If a customer reports a safety issue, tell them to contact emergency services.
> ```

> [tab] Sales
>
> **General**
>
> ```text theme={null}
> You are the sales assistant for Ledgerly, accounting software for small businesses.
> Help visitors understand the product, compare plans, and decide if it fits.
>
> - Ask what kind of business they run and how many people will use Ledgerly
>   before recommending a plan.
> - Describe plans and prices only as they appear in your training data.
> - When a visitor shows buying interest, offer to book a demo with the sales team.
> - Keep replies short: two to four sentences.
> ```
>
> **Guardrails**
>
> ```text theme={null}
> - Don't offer discounts or custom pricing.
> - Don't make claims about competitors.
> ```

> [tab] Ecommerce
>
> **General**
>
> ```text theme={null}
> You are the shopping assistant for Northpeak, an online store for outdoor gear.
> Help shoppers find products, answer sizing and shipping questions, and check orders.
>
> - Recommend products from your training data that match what the shopper
>   describes, and explain why each one fits.
> - For order status, ask for the order number before looking it up.
> - State shipping times and return rules exactly as your training data gives them.
> - If a shopper wants to return an item, explain the return policy, then
>   offer to start the return.
> ```
>
> **Guardrails**
>
> ```text theme={null}
> - Don't invent product features, stock levels, or delivery dates.
> - Don't recommend products from other stores.
> ```

Instructions only describe what the AI agent should do. To let it book a demo, look up an order, or start a return, add the matching [Actions](https://chatbase.co/docs/user-guides/chatbot/actions/actions-overview.md), such as [Calendly](https://chatbase.co/docs/user-guides/chatbot/actions/calendly.md), [Shopify Actions](https://chatbase.co/docs/user-guides/chatbot/actions/shopify-actions.md), or [Escalations](https://chatbase.co/docs/user-guides/chatbot/actions/escalate-to-human.md). For flows with several ordered steps, such as returns, use a [Procedure](https://chatbase.co/docs/user-guides/chatbot/procedures/procedures-overview.md).

### AI Model

The AI model is the specific machine learning model used to generate responses for your AI agent. Each model has different capabilities, performance characteristics, and message credit cost, so you can choose the one that best fits your needs.

> [accordion] Auto (Chatbase)
>
> Auto adapts to every conversation, giving instant answers for everyday questions and frontier-grade intelligence for demanding ones. Multilingual and image understanding are built in, and it handles tools end to end.
>
> * **Auto**: 1 message credit

> [accordion] GPT
>
> * **GPT-6.1 Sol**: 2 message credits
> * **GPT-6.1 Terra**: 2 message credits
> * **GPT-6 Luna**: 1 message credit
> * **GPT-5.6 Terra**: 2 message credits
> * **GPT-5.5**: 4 message credits
> * **GPT-5.2**: 2 message credits
> * **GPT-OSS-120B**: 1 message credit
> * **GPT-OSS-20B**: 1 message credit

> [accordion] Claude
>
> * **Claude 5.5 Opus**: 5 message credits
> * **Claude 5.5 Sonnet**: 2 message credits
> * **Claude 5.5 Haiku**: 1 message credit

> [accordion] Gemini
>
> * **Gemini 3.8 Flash**: 2 message credits
> * **Gemini 3.6 Flash**: 2 message credits
> * **Gemini 3.5 Flash Lite**: 1 message credit
> * **Gemini 3.1 Pro**: 2 message credits
> * **Gemini 3.1 Flash Lite**: 1 message credit
> * **Gemini 3 Flash**: 1 message credit
> * **Gemini 2.5 Pro**: 2 message credits

> [accordion] DeepSeek
>
> * **DeepSeek-V4.1-Flash**: 1 message credit
> * **DeepSeek-V4-Flash**: 1 message credit
> * **DeepSeek-V3.1**: 1 message credit
> * **DeepSeek-R1**: 1 message credit

> [accordion] Grok
>
> * **Grok 4.7**: 2 message credits

> [accordion] Mistral
>
> * **Mistral Medium 3.5**: 2 message credits
>
> * **Mistral Small 4**: 1 message credit
>
> > [!NOTE]
> >
> > When you choose a Mistral model, the main inference call that generates your AI agent's response runs on servers in the EU. Other steps involved in producing and delivering the reply may still be processed outside the EU, so selecting a Mistral model does not by itself keep all conversation data in the EU.

> [accordion] Kimi
>
> * **Kimi K2.6**: 1 message credit

> [accordion] GLM
>
> * **GLM 5.3 Flash**: 1 message credit
> * **GLM 5.2**: 2 message credits

> [!TIP]
>
> For help choosing between them, see the [models comparison](https://chatbase.co/docs/user-guides/chatbot/models-comparison.md) page.

### Temperature

Temperature controls how creative and varied your AI agent's responses are. The setting ranges from 0 to 1 and directly affects response predictability:

* **Lower temperature (close to 0)**: Produces focused, consistent responses by selecting the most probable outputs
* **Higher temperature (closer to 1)**: Generates more creative and varied responses with less predictability

Drag the slider between **Reserved** and **Creative** to set the value.

> [!NOTE]
>
> The default temperature is 0. Adjust it to experiment with different response styles and find what works best for your use case.

#### How temperature changes answers

Temperature changes how an answer is worded, not what the AI agent knows. Suppose a customer asks "What are your opening hours?" and your Data Sources say you're open 9 AM to 6 PM, Monday to Friday:

* **At 0**, the AI agent gives much the same answer each time: "We're open Monday to Friday, 9 AM to 6 PM."
* **Near 1**, the wording changes from one conversation to the next: "Happy to help! You can visit us any weekday between 9 in the morning and 6 in the evening."

Keep temperature low for support, billing, and policy questions, where customers should get the same answer every time. Raise it if replies feel repetitive in conversations where variety helps, such as product recommendations. To see the difference with your own content, open **Compare** and give two chats the same model at different temperatures.

## Compare area

Click **Compare** in the **Build > Instructions** header to open the compare view.

![Instructions Compare view](https://mintcdn.com/chatbase/St1vNiMgEx0Vl5Y7/user-guides/chatbot/images/playground/playground-compare.png?fit=max\&auto=format\&n=St1vNiMgEx0Vl5Y7\&q=85\&s=75bdf280c56afe4369248cb68611e157)

The Compare area lets you put several versions of your AI agent side by side and give each its own settings, which makes it much easier to work out which settings suit you. The same message is sent to every chat, so you can test the AI agent's response to identical input under different settings.

### Per-agent controls

Each chat box in the compare view has its own controls, from left to right:

| Control | What it does |
| - | - |
| **Sync** | Untick it if you don't want the message sent to this AI agent to be mirrored to the other chats |
| **Settings** | Adjust the AI model, temperature, and prompt for this AI agent only |
| **Save** | Save the settings you've assigned here to the main AI agent's settings |
| **Three dots** | Move the AI agent left or right, reset the chat, or delete the chat box |

![Instructions Compare view actions](https://mintcdn.com/chatbase/St1vNiMgEx0Vl5Y7/user-guides/chatbot/images/playground/playground-compare-actions.png?fit=max\&auto=format\&n=St1vNiMgEx0Vl5Y7\&q=85\&s=85eab01a5f91d26e5d60bea0cb7ecf69)

### View controls

You can also:

* Clear all chats
* Reset the AI agent's settings to the main settings
* Add a new AI agent to test with
* Click the filter icon to change which AI models you're testing, and select a new model from the dropdown

> [!TIP]
>
> Send the same question to two or three models at once and compare the answers before you commit to one in **Model configuration**.

## Troubleshooting

> [accordion] This agent is currently unavailable. If you are the owner please check your account
>
> **Possible cause:** you've run out of message credits.
>
> **Solution:** purchase add-on message credits. See [Add-ons](https://chatbase.co/docs/user-guides/workspace/settings.md#add-ons) for details.

## Frequently asked questions

> [accordion] What's the difference between instructions and Procedures?
>
> Instructions apply to every conversation: the AI agent's role, tone, scope, and rules. A [Procedure](https://chatbase.co/docs/user-guides/chatbot/procedures/procedures-overview.md) applies only when a conversation matches its trigger, and gives the AI agent an ordered list of steps to follow, including the Actions to call. Use instructions for how your AI agent behaves in general, and Procedures for situations like refunds or order issues where you don't want it improvising.

> [accordion] How long can my AI agent's instructions be?
>
> Instructions can be up to 30,000 characters, whether you write them in the dashboard or set them through the [Chatbase API](https://chatbase.co/docs/api-reference/v2/overview.md). Shorter instructions are easier to maintain: put facts like prices and policies in your [Data Sources](https://chatbase.co/docs/user-guides/chatbot/data-sources.md), and keep instructions for behavior.

> [accordion] Can each channel have different instructions?
>
> Yes. In the [Playground](https://chatbase.co/docs/user-guides/chatbot/playground.md#instructions-and-global-instructions), the **Overview** tab of each channel has **Sync with global instructions**. Leave it on to use the instructions from **Build > Instructions**, or turn it off to write instructions for that channel only.

> [accordion] Why don't my instruction changes show up for customers?
>
> Saving puts your changes in a draft. The Playground uses the draft right away, but your live channels keep the published version until you click **Publish**. See [Drafts and versions](https://chatbase.co/docs/user-guides/chatbot/versions.md).

> [accordion] Which AI model should I choose?
>
> If you're not sure, start with **Auto**, which uses 1 message credit per reply and adapts to each conversation. To compare specific models, send the same questions to several of them in **Compare**, and see [Models comparison](https://chatbase.co/docs/user-guides/chatbot/models-comparison.md) for each model's strengths.

> [accordion] Should I put rules in General or Guardrails?
>
> Put context and everyday behavior in **General**: your business, the AI agent's role, tone, and goals. Put non-negotiable rules in **Guardrails**, such as topics to avoid, information never to share, and compliance requirements. The **Guardrails** instructions field is different from the [Guardrails](https://chatbase.co/docs/user-guides/chatbot/guardrails.md) page, which covers rate limits, spam detection, and country blocking.

## Next steps

> [card] [Data Sources](https://chatbase.co/docs/user-guides/chatbot/data-sources.md)
>
> Add and manage the content your AI agent is trained on.

> [card] [Models comparison](https://chatbase.co/docs/user-guides/chatbot/models-comparison.md)
>
> See how the available models differ before you commit to one.

> [card] [Best Practices](https://chatbase.co/docs/user-guides/quick-start/best-practices.md)
>
> Proven ways to improve your AI agent's answers.

> [card] [Playground](https://chatbase.co/docs/user-guides/chatbot/playground.md)
>
> Preview the effect of your changes the way a visitor will see them.


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