2 articles tagged with "Tool Calling"

Picture an online store with a small support team. Much of the inbox is some version of "where is my order", and every answer means opening the order system and copying a status into a reply. You've used ChatGPT, maybe called an AI API once, and now the team wants an agent to take that first pass.

This guide shows you how to build AI agents in Node.js by building that one, a piece at a time. By the end it looks orders up by itself, asks a person before it gives money back, and keeps answering when an AI service goes down. You start on your laptop with no API key and move to a hosted model when you're ready.

We ran every example on a deliberately tiny model and show you where it got things wrong. Those mistakes are much cheaper to meet here than in front of a customer.

Picture the support inbox at an online retailer on a Monday morning. Ticket after ticket asks the same thing: where is my order? Each one means a rep checks the order, then the carrier, then types a reply.

A plain chatbot can't help. It doesn't know your orders, so it guesses. An AI agent can look things up on its own and hand anything risky to a person. This guide shows how to build an AI agent in Python for that job, without a big framework.

You'll start with the idea, write the agent in one file, run it on a hosted model and on a free one on your laptop, then add the checks you'd want before customers see it. Along the way, a tiny local model shows where things quietly go wrong.