Choosing your AI agent’s completion model
The instructions below are for desktops and laptops only.
You can choose the completion model your AI agent uses when generating responses. This gives you more control over how each AI agent performs based on your support needs.
For example, you can choose a faster, more cost-efficient model for simple customer queries, or a stronger model for AI agents that handle more complex conversations.
Each AI agent has its own completion model setting, allowing you to customize agents independently.
For example, you can choose a faster, more cost-efficient model for simple customer queries, or a stronger model for AI agents that handle more complex conversations.
Each AI agent has its own completion model setting, allowing you to customize agents independently.
Before you start
Ensure you have enabled AI Assist and created an AI agent.
To learn more about setting up AI Assist and configuring your AI agent, see this guide:
Getting started with AI Assist
To learn more about setting up AI Assist and configuring your AI agent, see this guide:
Getting started with AI Assist
Steps to choose the agent’s completion model
2. Click Automation on the left navigation bar.
3. Click Agents in the left submenu.
4. Select your AI agent.
6. Select your preferred model from the dropdown list.
7. Your changes are saved immediately.
Use the widget preview on the right to test your AI agent’s responses.
How it works
The selected completion model is saved individually for each AI agent and used whenever that agent generates a response.
You can assign different AI agents with different models depending on their purpose. For example:
New AI agents use GPT-4.1 mini as the default completion model. You can also select GPT-4o mini if you prefer faster responses with lower costs.
You can assign different AI agents with different models depending on their purpose. For example:
- Use a faster model for an AI agent that handles simple, frequently asked questions.
- Use a stronger model for an AI agent that needs to handle more detailed or complex conversations.
New AI agents use GPT-4.1 mini as the default completion model. You can also select GPT-4o mini if you prefer faster responses with lower costs.
Additional considerations
- Each AI agent has its own completion model setting. Changing the model for one AI agent does not affect other AI agents in the same property.
- The completion models available in the dropdown may change as new options become available.
Related guides
AI Assist: 24/7 sales and customer service made easy
Getting started with AI Assist
Getting started with the Base Prompt
Modifying the Base Prompt
Understanding the Base Prompt
Using Base Prompt to restrict AI Assist's responses
Using Base Prompt instructions for escalation
Using Base Prompt instructions for lead capture
Using Base Prompt to direct visitors to search result pages
Fixing incorrect responses delivered by AI Assist
Getting started with AI Assist
Getting started with the Base Prompt
Modifying the Base Prompt
Understanding the Base Prompt
Using Base Prompt to restrict AI Assist's responses
Using Base Prompt instructions for escalation
Using Base Prompt instructions for lead capture
Using Base Prompt to direct visitors to search result pages
Fixing incorrect responses delivered by AI Assist
If you have feedback about this article, or if you need more help:
- Click the green live chat icon
- Schedule a call with us
- Visit our community