Configure and use Understanding mode

What is Understanding mode?

Understanding enhances your AI agent’s ability to understand and respond to multi-layered queries by breaking them down into smaller components. This improves the depth, relevance, and accuracy of the responses—especially in content-rich environments.

🚧

Note:

This feature is available exclusively for users on Premium and Enterprise plans.

How Understanding mode works:

• The agent breaks down user queries into five sub-queries, isolating key components to better understand the user's intent.
• A vector database is queried for each sub-query individually to retrieve the most relevant data.
• The retrieved contexts are merged into one, providing comprehensive insights.
• This process adds a slight latency of up to 1-2 seconds due to the enhanced processing.

When to use Understanding mode:

• Best suited for complex, multi-dimensional queries where advanced insights are required.
• Ideal for projects where the system needs to anticipate user needs and provide in-depth responses.
• Avoid enabling for simple queries, as it might add unnecessary latency without significant benefits.

Key benefits of Understanding mode:

• Enhanced Understanding: The agent can handle multi-dimensional queries by breaking them into smaller, manageable parts.
• Improved Response Quality: Merging results from sub-queries ensures the response is thorough and contextually relevant.
• Forward-Thinking AI: Anticipates user needs, delivering insights beyond the immediate query.

How to enable Understanding mode:

1. Click Personalize.

2. Click AI Intelligence tab.

3. Click Understanding to enable this feature for your agent.

4. Under select your AI model, choose the model for your agent:

• GPT-4.1
• GPT-4o
• GPT-5.1 Optimal
• GPT-5.1 Smart
• GPT-5.2 Optimal
• GPT-5.2 Smart
• Claude 4.5 Opus
• Claude 4.6 Opus
• Claude 4.5 Sonnet
• Gemini 3 Pro

5. Click Save Settings to apply the changes.