Model
The trained file of learned parameters that turns input into output.
A model is the learned artefact itself: a set of parameters plus the code needed to run them. It does one thing, which for a language model is predicting the next token. It cannot read your files, run your commands, or remember yesterday on its own. Everything that feels like an agent working is the surrounding software supplying those capabilities. That is why the same model behaves differently in two products: the model did not change, the surroundings did.
Related terms
Parameters
The learned numbers inside a model. Their count is the model size.
Inference
Running a trained model to produce an answer. What happens on every request.
LLM
A model trained on a huge amount of text to predict the next token. The engine behind most AI products.
Harness
Everything around the model that turns it into an agent: tools, system prompt, permissions, hooks.
Want this working inside your team?
It starts with one conversation about your workflow.