4 articles
A four-dimension checklist — trigger, structure, steering, pruning — for evaluating whether an AI agent skill actually steers behavior or just burns context-window tokens.
An agent loop is a system where an AI coding agent repeatedly works toward a specified goal without waiting for human approval between each step — you define the trigger and the stopping condition, and the agent runs autonomously.
Browser Use is a family of techniques and tools — led by the open-source Python library browser-use — that lets AI agents control a real web browser the way a human would, all described in natural language.
Function calling (also called tool use) is a capability that lets an LLM output structured commands — like get_weather(location='Cairo') — which your own code then executes, bridging the gap between what the model says and what it can do.