Glossary
LLM (large language model)
Definition
What is LLM (large language model)?
A large language model, or LLM, is an AI model trained on vast amounts of text to understand and generate language. Models such as Claude, GPT and Gemini power today's assistants and agents. In business automation an LLM is the component that reads, classifies, extracts and writes; it is not a database and does not know your data unless you give it.
Last updated:
Choosing a model for a business task
The strongest model is not always the right one. Classification and extraction at volume run well on smaller, faster models; drafting client-facing text or handling ambiguous cases justifies a frontier model. We benchmark on your real data before choosing.
Frequently asked questions
Is my data used to train the model?
Not with the commercial APIs we use, whose terms exclude customer data from training. We confirm this per provider in the data processing agreement.
Related terms
Further reading
Workflows
Related services
Have a process like this? Tell us about it.
Book a call