Lesson 2: From Chatbot to Agent
A note on this series. This is written for beginners, on purpose. I’m keeping explanations at a practical, conceptual level rather than a technical one. Several ideas here are described in generic terms rather than their full technical depth. The goal of these seven lessons is to demystify AI agents enough that the hype becomes understandable and ideally to spark enough curiosity that you go looking for the deeper technical material afterward.
In Lesson 1 I established that a language model predicts text and nothing more. That leaves the term “AI agent” to explain, and why it’s replacing “chatbot” or “assistant” everywhere right now.
The boundary isn’t a hard line. Real systems sit on a spectrum. A workflow can contain an LLM without being an agent, and a chat-based assistant can use tools without becoming a fully autonomous agent. The useful question isn’t “Is this definitely a chatbot or definitely an agent?” It’s “How much of the workflow does the system decide for itself, what tools can it use, and how much human control remains?”
The chatbot: talk in, talk out
A basic chatbot takes your question and gives you an answer. In its simplest form, the interaction is closed: you ask, it responds, and nothing happens outside the conversation. More capable chat-based systems can also use tools, so the boundary between ‘chatbot’ and ‘agent’ isn’t always clean.
The agent: talk in, action out
An agent is a system built around a model, but wired up so the model’s output can trigger real actions: searching the web, running code, reading a file, calling an API, sending an email, updating a spreadsheet. The model still generates outputs, but those outputs can include structured tool calls or other actions that the surrounding software executes..
MIT Sloan describes this as AI that can perceive, reason, and act largely on its own, rather than waiting to be asked a single question and answering it. Forrester’s framing is a bit more blunt: a working agent behaves less like a chatbot and more like a small piece of infrastructure, something that has to plan, coordinate, and keep running across multiple steps (Forrester, 2026).
A simple industry example makes the distinction concrete: a chatbot tells you how to book a meeting. An agent checks the calendar, finds an open slot, sends the invite, and books the room, without you doing each of those steps by hand (Insentra, 2026).
What “autonomous” actually means here
“Autonomous” gets thrown around loosely. In practice, autonomy means the system can make some decisions and carry out multiple steps toward a goal without a human directing every step. How much of the workflow it chooses itself varies from system to system. Give it a goal “find three vendors and compare their pricing” and it decides on its own how to break that into steps: search, extract, compare, summarize. You didn’t write those steps. It figured them out.
That’s a totally different capability than a chatbot answering one question at a time, and it’s also where a lot of new risk shows up. More on that later in the series.
Not every “AI agent” on the market deserves the name
As a novice, be skeptical here. The term “agent” is being slapped on a lot of products that don’t really do autonomous multi-step reasoning. Gartner has estimated that of the thousands of vendors marketing ‘AI agents,’ only a small fraction, roughly 130, currently offer systems that genuinely meet its definition of agentic AI.
A broader warning is useful with the word ‘agent’ being applied to a wide range of products (MachineLearningMastery, 2026). The industry has a term for it: agent washing.
The gut check is whether the system decides its own steps, or just follows a fixed script a human wrote in advance. Fixed scripts triggered by AI “if this email arrives, draft this reply” are useful automations, but they aren’t agentic in the sense this series is building toward. Real agentic behavior means the model itself chooses what to do next based on what it observes.
What to carry into Lesson 3
- A chatbot answers. An agent acts, across multiple steps, toward a goal.
- Autonomy means the system decides its own steps, not that a human is absent entirely.
- Watch for “agent washing.” Ask whether a product actually reasons through steps or just runs a fixed script with an AI label on it.
Next lesson, I open up an agent and look at the four pieces every one of them is built from.