An AI agent is a program that gives a language model a goal, a set of tools and a loop: the model decides on a step, the program runs it, and the result goes back to the model until the task is done. The model is only one part. The rest is ordinary software that decides what the model sees, which tools it may call, when to stop and what happens when something fails.
These guides build that software in Python, starting with a working agent and then covering each piece in turn: the harness around the model, the system prompt, choosing a model for tool calling, keeping an agent's setup in a YAML file, and streaming its answers to a web client. Each guide explains the idea first and then shows runnable code with Promptise Foundry. Start with the first guide if you are new to agents; the others can be read in any order.
The code in these guides runs on Promptise Foundry, an open-source Python framework for AI agents and MCP servers.