Skip to main content
Under the ‘LLM’ 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: GPT 5.2, GPT 5.2 Thinking, Claude Sonnet 4.6, Claude Sonnet 4.5, GPT 5.1, GPT 5.1 Thinking, GPT 4.1, GPT 5 Mini, or Claude Opus 4.6. Brief descriptions of each LLM can be found below their respective labels in the ‘LLM’ tab. Mindset Recommended (GPT-5.2): The default we recommend if you’re not sure which to pick. Balances cost, intelligence, and speed for most use cases, with strong performance across writing, analysis, and coding. GPT 5.2: OpenAI’s model for most professional work. Noticeably stronger at documents, long-context tasks, and multi-step projects. The reliable choice when quality and accuracy are essential. GPT 5.2 Thinking: The most powerful option in the GPT 5.2 family. Applies deeper reasoning behind the scenes to deliver more polished, accurate answers on your hardest tasks. Claude Sonnet 4.6: Thoughtful and creative. Very good at writing and analysis. Known for careful, well-reasoned responses and being the most creative. Claude Sonnet 4.5: Smart and reliable. A strong all-rounder for writing, analysis, and everyday professional tasks. Delivers well-reasoned, accurate responses without the wait. GPT 5.1: Warm and conversational with a natural, human feel. Great for brainstorming, drafting, and tasks where tone and engagement matter. Adapts its thinking on the fly for more accurate answers. GPT 5.1 Thinking: A more thorough version of GPT 5.1. Reasons more carefully behind the scenes before responding, delivering more accurate answers on complex tasks while keeping that warm, engaging feel. GPT 4.1: Great for everyday work. Handles most text tasks well, writing, answering questions, and coding. Good at remembering long conversations and following instructions carefully. GPT 5 Mini: Smart but affordable. Good intelligence at lower cost, with faster responses for routine tasks when you don’t need the strongest model. Claude Opus 4.6: Anthropic’s most capable model. Exceptional at complex reasoning, multi-step analysis, and ambitious tasks that require careful planning. Best when quality matters more than speed. 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.