Understanding AI Models for AI Agents in BoldDesk
When creating an AI Agent, administrators must select a model from the Model dropdown. The selected model serves as the AI Agent’s underlying intelligence and determines how the AI Agent interprets customer requests, processes information, and generates responses.
The Model field is mandatory. An AI Agent cannot be created without selecting a model.
The Model dropdown displays all AI models currently supported and available within your BoldDesk environment. Available models are organised by provider, making it easier to identify the source of each model and compare available options.
Different AI models are optimised for different scenarios and may vary in areas such as:
- Response speed
- Reasoning and problem-solving capabilities
- Instruction-following accuracy
- Knowledge retrieval and contextual understanding
- Multimodal capabilities, such as processing both text and images
Depending on your support requirements, you may choose a model that is better suited for handling simple customer enquiries, knowledge-based assistance, troubleshooting workflows, or more complex support interactions.
The following sections describe the AI models currently available for AI Agents, organized by provider, along with their capabilities and recommended use cases.
Azure OpenAI / OpenAI GPT
Use Azure OpenAI / OpenAI GPT models when your AI Agent requires advanced reasoning, conversational support, coding assistance, professional workflows, or an optimal balance between performance and cost.
| Model | Description |
|---|---|
| GPT-5.2 | An earlier-generation GPT-5 model suitable for general-purpose AI tasks. |
| GPT-5.4 | A frontier model designed for professional work, advanced reasoning, coding, and agentic workflows. |
| GPT-5.4 Mini | A smaller GPT-5.4 variant that provides a balance between performance and cost efficiency. |
| GPT-5.4 Nano | A lightweight GPT-5.4 variant optimized for simple, high-volume, or cost-sensitive workloads. |
| GPT-5.4 Pro | A high-performance GPT-5.4 variant designed for complex tasks that require stronger reasoning and advanced capabilities. |
Best Practices
Follow these recommendations when selecting a model for an AI Agent:
- Choose a model that aligns with the AI Agent’s intended purpose and responsibilities.
- Use advanced reasoning models for complex troubleshooting, decision-making, or workflow automation scenarios.
- Select lighter or faster models for straightforward, repetitive, or high-volume support interactions.
- Maintain consistency when configuring AI Agents with similar roles and responsibilities.
- Test the AI Agent thoroughly before deploying it to customer-facing channels.
- Regularly review generated responses to ensure the selected model meets your expectations for accuracy, tone, and response quality.
Troubleshooting
The Model dropdown is empty
Verify that AI models have been configured and enabled in your BoldDesk environment. The Model dropdown displays only the models that are currently available and assigned to your environment.
A specific model is not listed
If a model does not appear in the Model dropdown, it may not be enabled or supported in your BoldDesk environment. Available models depend on the configured AI providers, such as Amazon Bedrock, Google Gemini, and Azure OpenAI.
AI Agent responses are slow
If response time is a concern, consider selecting a faster or lighter model that is better suited for simple or repetitive support requests. Evaluate performance through testing before deploying the AI Agent to production environments.
AI Agent responses do not meet expectations
Review the selected model and test the AI Agent using realistic support scenarios. If responses do not meet your requirements for accuracy, tone, or reasoning quality, consider switching to a model that is better suited for the intended use case.
Frequently Asked Questions
-
What is the Model field used for when creating an AI Agent?
The Model field specifies the AI model that powers the AI Agent. The selected model influences how the agent interprets requests, reasons through support scenarios, and generates responses. -
Is selecting a model required when creating an AI Agent?
Yes. The Model field is required and must be configured before an AI Agent can be created. -
Why do I see different models in the Model dropdown?
The models displayed in the Model dropdown depend on the providers and models enabled in your BoldDesk environment. Supported providers may include Amazon Bedrock, Google Gemini, and Azure OpenAI. -
Can different AI Agents use different models?
Yes. Each AI Agent can be configured with a different model based on its specific purpose. For example, one AI Agent might use a lightweight model for common inquiries, while another uses an advanced reasoning model for technical troubleshooting. -
How do I choose the right model for an AI Agent?
Select a model based on the AI Agent’s intended use case, expected query complexity, performance requirements, and desired response quality. Testing with real-world scenarios is recommended before deployment. -
Does the selected model affect AI Agent performance?
Yes. The selected model can affect response quality, reasoning capability, speed, cost efficiency, and the AI Agent’s ability to handle both simple and complex support interactions.
