← Back to glossarymodels
LLM
A Large Language Model is a neural network trained on billions of texts that understands, generates and transforms language. GPT-4, Claude, and Mistral are examples.
Also known as: Large Language Model, Sprachmodell
In detail
LLMs are the engine behind modern AI agents. They take text as input and produce text as output — but they can do more than just continue: summarize, translate, classify, write code, interact with structured tools.
We primarily use:
- Anthropic Claude (via AWS Bedrock EU) for most agent tasks
- OpenAI GPT where needed (on customer request)
- Mistral as a European alternative
- Llama 3 as a self-hosted option for particularly sensitive data
Example
An LLM receives: 'Write a polite rejection for candidate X.' and produces a complete, context-aware letter in 2 seconds.
Related terms
- Context windowThe context window is the maximum amount of text (measured in tokens) a language model can process at once — typically 128k to 1M tokens with current models.
- Fine-tuningFine-tuning is the additional training of an already-trained language model on your own data — changes the model itself, unlike RAG.
- AI agentAn AI agent is a program built on a language model that completes tasks on its own: it understands a request, plans steps, calls tools, and responds with a result instead of just text.