A context window is the maximum amount of text, counted in tokens, that a language model can take into account in one request. It covers the instructions, the conversation, any retrieved documents and the reply.
A large language model (LLM) is a neural network trained on very large amounts of text to predict and generate language. It powers chat assistants, summarisers, coding tools and AI agents.
Prompt engineering is the practice of designing and testing the instructions, context and examples given to a language model. The aim is reliable, useful output.
Retrieval-augmented generation (RAG) is a pattern that hands a language model relevant passages from your own documents at question time. Its answers then rest on that material, not only on what it learnt in training.
In AI, tokenization is splitting text into small units called tokens, such as words or word pieces, which a language model reads and generates. Token counts set how much text fits in a model's context window and usually drive the cost of each API call.
A transformer is a neural network architecture that uses attention to weigh the relationships between all parts of an input. It is the basis of most modern language models.
A clear proven process, that delivers
You've seen our ideas - now go deeper.
Discover more insights, guides, and engineering practice.