What is an LLM?
An LLM (large language model) is an AI model trained on very large amounts of text that answers questions, summarises, translates and writes by predicting what text should come next. OpenAI GPT, Anthropic Claude and Google Gemini are well-known examples. Businesses use them to classify email, summarise documents and draft replies to customers.
Definition
An LLM (large language model) is an AI model trained on very large amounts of text that answers questions, summarises, translates and writes by predicting what text should come next.
How does an LLM work?
An LLM splits text into small units called tokens and, at each step, predicts the most likely next token. Billions of parameters let those predictions capture grammar, context and general knowledge. However capable the model is, its knowledge stops at its training cut-off and it knows nothing about your internal information. That gap is usually closed with RAG.
Where do businesses use LLMs?
In repetitive text work that rules cannot handle: routing incoming email by topic, extracting clauses from contracts, summarising meeting notes, drafting replies to customers. An LLM is rarely a product on its own. It creates the most value as a step inside a workflow automation or an AI agent.
Choosing a model
Commercial models are reached through APIs from OpenAI, Anthropic, Google or Azure OpenAI. When data must not leave a given jurisdiction, open-weight models such as Llama, Mistral or Qwen can run on your own servers. For teams in Türkiye, models adapted to Turkish are also published on Hugging Face. The choice is shaped by data protection requirements (GDPR in the EU, KVKK in Türkiye), language quality and cost. The tendency to produce confident but wrong answers is called hallucination.
Related terms
- RAG (Retrieval-Augmented Generation)RAG (Retrieval-Augmented Generation) is an AI architecture that lets a language model retrieve relevant passages from a chosen document collection, such as a company's own documents, and use them as context before it writes an answer.
- Prompt engineeringPrompt engineering is the practice of writing, testing and refining the instructions, examples and context given to a language model so that it produces consistent, accurate results.
- Fine-tuningFine-tuning is the process of further training a pre-trained AI model on your own examples so that it performs a specific task, tone or output format better.
- AI hallucinationAn AI hallucination is output in which a language model presents information, a source or a figure that does not exist, fluently and confidently, as if it were true.
- EmbeddingAn embedding is a fixed-length array of numbers (a vector) that represents the meaning of a word, sentence, document or image, so that similar content ends up close together.
Frequently asked questions
Can LLMs handle Turkish and other non-English languages?
Leading commercial models generally read and write Turkish well. For legal or industry-specific terminology and for long documents, you should still test with your own examples before going live.
Is it safe to send company data to an LLM provider?
That depends on the provider's enterprise terms, the region where data is processed and whether your data is used for training. For personal data, review international transfer rules with your legal adviser; where needed, an open-weight model can run on your own infrastructure.
Let’s talk about your transformation
Tell us which work repeats every week. We will tell you honestly whether it is worth automating.
How we start
- A free first callWe pin down the problem and the goal together.
- A 2-week discovery sprintWe look at the data, the process and the tools, and decide where to start.
- A written proposalScope, architecture and timeline, in writing.