LLM (Beta)

Learn about the different LLM options within the Agent feature.

Under the 'LLM (Beta)' tab in the agent configuration, administrators can select the Large Language Model (LLM) that best aligns with the agent’s objectives. The selected model will dictate the agent's responses to user queries.

Large Language Models are AI systems that understand and generate human language, enabling tasks like text generation, question answering, and translation in a specific way.

Currently, you can select from the following LLM options: Mindset Recommended, GPT4o, Gemini 1.5 Pro, Claude 3 Sonnet, or Llama 3.1 405B Chat. Brief descriptions of each LLM can be found below their respective labels in the 'LLM (Beta)' tab.

GPT 4o

It’s ideal for creating AI agents that require deep problem-solving and natural human-like interactions.

Best for:

• Virtual assistants for customer support and engagement

• content creation agents for blogs, social media, and marketing

• AI-powered coding assistants

• Research and data analysis

Gemini 1.5 Pro

It’s perfect for AI agents that need deep contextual awareness.

Best For:

• AI search and knowledge retrieval agents

• Multimodal assistants capable of processing text, images, and code

• Creative and analytical AI solutions

Claude 3 Sonnet

Known for its strong reasoning, ethical AI principles, and document processing skills, Claude 3 Sonnet is perfect for AI agents who require high-level decision-making and in-depth analysis.

Best For:

• Legal and financial AI advisors for document review and compliance

• Research assistants for summarization and knowledge retrieval

• Business intelligence agents for data-driven insights

Llama 3.3 70B

It provides flexibility for tailored implementations.

Best For:

• Custom Agents with specialized business logic

• Knowledge management and internal automation agents

• Open-source AI development

• Cost-effective AI-driven customer interactions

We advise you to first trial each of these models in the 'Preview' tab to evaluate their performance and ensure satisfaction with the generated response outputs.

Additional information on these Large Language Model options can be found by contacting your Customer Success Representative.