Skip to main content

​
Overview

Build is where you configure everything your agent needs to operate. 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:
Two different things are called guardrails. The Guardrails instructions field on this page holds behavioral rules you write for the agent. The separate Guardrails page covers abuse protection: rate limits, spam detection, and country blocking.

​
Instructions

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

​
General instructions

The General section contains your agent’s primary instructions. Use this section to define:
  • Your business or product context
  • The agent’s role and responsibilities
  • Response style and tone
  • Goals and expected behavior
  • Any additional guidance the agent should follow
These instructions serve as the foundation for your agent’s responses.

​
Guardrails instructions

Use Guardrails to define rules your agent should always follow. Examples include:
  • Restricting topics the agent can discuss
  • Preventing the disclosure of sensitive information
  • Defining safety or compliance requirements
  • Controlling fallback behavior
  • Limiting the agent’s role or capabilities
Guardrails are intended for non-negotiable rules that should apply to every conversation.
Start with a simple, clear description of your 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.

​
AI Model

The AI model is the specific machine learning model used to generate responses for your agent. Each model has different capabilities, performance characteristics, and message credit cost, so you can choose the one that best fits your needs.
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
  • GPT-5.2: 2 message credits
  • GPT-5 Mini: 1 message credit
  • GPT-5 Nano: 1 message credit
  • GPT-5.5: 4 message credits
  • GPT-OSS-120B: 1 message credit
  • GPT-OSS-20B: 1 message credit
  • GPT-4o Mini: 1 message credit
  • GPT-5.6 Luna: 1 message credit
  • GPT-5.6 Terra: 2 message credits
  • Claude 4.6 Opus: 5 message credits
  • Claude 4.6 Sonnet: 3 message credits
  • Claude 4.5 Haiku: 1 message credit
  • Claude 4.5 Sonnet: 3 message credits
  • Claude 4.5 Opus: 5 message credits
  • Claude 4.7 Opus: 6 message credits
  • Claude 4.8 Opus: 6 message credits
  • Gemini 3.1 Pro: 2 message credits
  • Gemini 3.1 Flash Lite: 1 message credit
  • Gemini 3 Flash: 1 message credit
  • Gemini 3.5 Flash: 2 message credits
  • Gemini 3.5 Flash Lite: 1 message credit
  • Gemini 3.6 Flash: 2 message credits
  • Gemini 2.5 Pro: 2 message credits
  • Llama 4 Scout: 1 message credit
  • Llama 4 Maverick: 1 message credit
  • DeepSeek-V3: 1 message credit
  • DeepSeek-R1: 1 message credit
  • DeepSeek-V4-Flash: 1 message credit
  • Grok 4: 4 message credits
  • Grok 3: 3 message credits
  • Grok 3 mini: 1 message credit
  • Mistral Medium 3.5: 2 message credits
  • Mistral Small 4: 1 message credit
  • KimiK2: 1 message credit
  • GLM 5.2: 2 message credits
For help choosing between them, see the models comparison page.

​
Temperature

Temperature controls how creative and varied your 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.
The default temperature is 0. Adjust it to experiment with different response styles and find what works best for your use case.

​
Compare area

Click Compare in the Build > Instructions header to open the compare view.
Instructions Compare view
The Compare area lets you put several versions of your 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 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:
Instructions Compare view actions

​
View controls

You can also:
  • Clear all chats
  • Reset the agent’s settings to the main settings
  • Add a new agent to test with
  • Click the filter icon to change which AI models you’re testing, and select a new model from the dropdown
Send the same question to two or three models at once and compare the answers before you commit to one in Model configuration.

​
Troubleshooting

Possible cause: you’ve run out of message credits.Solution: purchase add-on message credits. See Add-ons for details.

​
Next steps

Data sources

Add and manage the content your agent is trained on.

Models comparison

See how the available models differ before you commit to one.

Best Practices

Proven ways to improve your agent’s answers.

Playground

Preview the effect of your changes the way a visitor will see them.