Module 1 Lesson 2 - What an AI Agent Actually Is

📌 Read time: ~7 min | Module 1 of 8

---

Let's Be Precise

There is a lot of noise around "AI agents." Vendors call everything an agent. Chatbots get called agents. Automation platforms get called agents. Most of it is marketing.

Here is the working definition we will use in this course:

An AI agent is a software system that perceives its environment, reasons about what to do, takes actions using tools and loops — until it reaches a goal or determines it cannot.

Four words matter: perceives, reasons, acts, loops. Take away any one of them and you have something else.

---

The Four Pillars

Think about how you troubleshoot a network problem you have never seen before. You are not running a script. You are doing something more sophisticated. Let's name it.

Pillar 1: Reasoning Engine

This is the brain. For you, it is 10 years of network experience. For the agent, it is a large language model — Claude, GPT-4, Llama. It understands concepts and decides what step to take next. Not magic — a very good pattern-matcher that has read every RFC, every Cisco TAC document, and every BGP Stack Overflow answer ever written.

Pillar 2: Memory

When you walk into a client's NOC for the first time, you are less effective than after six months running that network. The difference is your mental model. An agent has the same concept. An agent without memory starts from zero every time.

Pillar 3: Tools

Knowing what to do is not the same as being able to do it. Tools are the agent's hands — SSH execution, API calls to your SNMP queries, log fetching, ticket creation. The agent does not run tools blindly. The reasoning engine decides which tool to call, with which parameters, based on what it has found so far.

Pillar 4: Context

Everything the agent knows at the moment it is working — the client's network documentation, previous ticket history, the output of the last five commands it ran. When you give your agent good context, it performs like your best engineer. When you give it no context, it guesses.

---

The Perception-Action Cycle

This is how an agent actually runs. Not once. In a loop.

GOAL SET → PERCEIVE → REASON → ACT → Goal reached?

NO ← loop back

YES → STOP

Every pass through that loop is one step. A real troubleshooting run might take 8-15 steps. Each step is the agent reading new information and deciding what to do with it.

---

This Is Not a Chatbot

A chatbot answers questions. You ask, it responds. End of interaction.

An agent investigates and acts. You give it a goal. It SSHes into routers, runs commands, correlates outputs, identifies root cause, drafts a fix, opens a ticket with the full diagnostic trace.

The difference is not the AI model underneath. It is the loop. Chatbots answer once. Agents keep going.

When someone shows you a ChatGPT demo answering "why is my OSPF down" — that is a chatbot being smart. Impressive but it cannot log into your router.

That is what we are building in this course.

---

👇 What's next: Lesson 3 — How Your Agent Will Reason

0 comments