Skip to content

Large language model (LLM)

A large language model is an AI model trained on large amounts of text to understand and generate language, such as OpenAI's GPT models, Anthropic's Claude and Google's Gemini.

LLMs are the engine inside most business AI tools: drafting emails, summarizing documents, extracting fields, classifying requests and answering questions. For a business, the model is usually one component of a larger system that also includes your data, integrations, permissions and tests.

For example, the same LLM could summarize a sales call in the CRM and classify an incoming supplier email, with different instructions and access for each. The misconception is that an LLM knows your business. It knows nothing about your customers, prices or policies unless that information is supplied with the request, and it can state wrong things confidently, which is why grounding and evals matter.

Bring us a workflow.

Tell us where the work slows down. We will help you see where to start.

Book a discovery call