Foundations

What is a large language model?

LLMs power most of the recent AI wave, from chatbots to document processing. They are rented by usage, so cost scales with how much text you send and receive.

In plain terms

A large language model is an AI system trained on vast amounts of text that can read, write, summarize, and answer questions in natural language.

Also called LLM.

A large language model is a system trained on a huge amount of text so it can continue a conversation, draft a document, or follow an instruction in ordinary language. ChatGPT, Claude, and Gemini are products built on these models. The model does not look up your company files unless you connect them.

Treat it as a very fast junior colleague who has read widely and has no memory of your business. It writes well. It also fills gaps with something that sounds right. You use it to draft, summarize, and sort. You do not let it invent a price, a legal position, or a medical instruction on its own.

Think of it this way: An LLM is like a brilliant generalist who has read every book, manual, and website ever published. They summarize and draft with confidence, but they sometimes confuse what they read with what is true.

A legal firm uses an LLM to draft first-pass responses to routine client queries, cutting paralegal hours on standard correspondence by 60 percent.

A professional-services firm pastes a 40-page request for proposal into a model and asks for a first-draft response. The draft is a useful start. A partner still checks every claim against the firm's actual projects, because the model will otherwise describe work the firm never did.

For any task involving reading, writing, summarizing, or classifying natural language: customer support drafts, document review, internal Q&A, and code generation. For precise numerical calculations, real-time data lookups, or anywhere a confident-sounding wrong answer could cause harm without a human check in place.

You do not need to pick a model from this page. RaftLabs starts from the job: the documents, the decision, and what a wrong answer costs. You see a working version before a large build. The related work on our side is LLM integration.

This sits with the other foundations terms on the glossary. The words under every AI conversation, from the model itself to the data it learned from. Worth reading next: Artificial Intelligence (AI), Machine Learning (ML), and Generative AI.

Common questions

Almost never. Training one from scratch costs more than most companies will save. You rent a model and spend the budget on your documents, your checks, and the workflow around it. Build your own only if the model itself is the product and you have the data and the money to keep it current.
Not unless you give them to it, on purpose, for that request or through a search step that pulls the right pages. Pasting a file into a public chat can also put that file in the vendor's hands. Ask where the text is stored before anyone pastes customer data.

Work with us

Tell us what's broken.

Tell us what's not working in your business. We'll find the real problem and tell you exactly what it would take to fix it.

  • Scope and cost agreed before work starts. No surprises. No obligation.
  • Working prototype within 3 weeks of kickoff.
  • Pay by milestone. You see progress before each invoice.
  • 60-day post-launch warranty. Bug fixes, UI tweaks, and deployment support. No retainer.
  • All conversations are NDA-protected.