LLM

A large language model is a neural network trained on vast amounts of text to understand and generate human language. Modern LLMs can also follow instructions, reason through problems, and use external tools.

LLMs are the reasoning engine behind AI agents. They parse unstructured inputs like emails and SMS, decide what action to take, and generate structured outputs for tools and databases. The quality of an agent depends heavily on the quality of the LLM and the prompts that guide it.

The OpsForEnergy system uses Claude Sonnet 4 as its backbone LLM. It was chosen for its strong performance on structured extraction, long context handling, and reliable tool use: all critical for operations workflows.