An AI Agent, is an LLM Tool calling process that calls AI Tools in a loop to achieve a given goal. Put simply an AI Agent is simply an AI that keeps calling AI Tools, either locally or through MCP, until is "thinks" its achieved the goal you
Tool calling is the process by which an LLM can use AI Tools When you ask an LLM a question, it generates an answer. The answer is generated on the GPUs hosted by the model provider, like OpenAI or Anthropic. So how is it able to call an AI Tool
MCP is the method by which AI Tools can be hosted on the internet and used by your AI Agents. AI Tools can either be used locally or hosted on the internet. When hosted on an API, we need some way to tell our AI which tools are available, and
An AI tool, is a piece of code, that an AI knows how to use. That' a fairly simple sentence to type out, but let's conceptualise it. When we write code, we create functions which do things, and then we string them together to make a program.
At this point, I think most of us understand that us developers spend more time reading code than writing it. And this is displayed clearly in practice. Before updating code or adding features, we will spend a decent amount of code identifying the change points, architecting things in our heads,