A chatbot answers. An agent acts — it plans, calls tools, observes what happened, and tries again until the job is done. That single difference is the reason "add an LLM" and "ship an AI system" are two completely different projects.

For two years the default AI experience was a text box: you ask, the model replies, and nothing in the world changes. Useful, but bounded. The model can't look anything up it wasn't trained on, can't touch your systems, and can't recover when its first answer is wrong. An agent closes that loop. Give a model a goal, a set of tools, and permission to run in a loop, and it stops being a conversationalist and becomes a worker.

The loop is the whole idea

Every agent, no matter how fancy, runs the same core cycle. Step through it below.

The agent loop

Click "Next step" to advance. Watch how an agent turns one goal into repeated, verified action.

🧭 Planbreak down goal🔧 Actcall a tool👁 Observeread result🔁 Reflectdone? or loop

Why the loop changes everything

A chatbot gets exactly one shot. An agent gets as many as it needs — and, crucially, it can check its own work between attempts. On tasks that require looking something up, using a calculator, or touching a real system, that difference is enormous. Here is roughly what we see when the same underlying model is given the same multi-step tasks, first as a single-shot chatbot and then as a tool-using agent.

Chatbot vs. agent — task completion

Drag the slider to change task difficulty (number of steps required). Watch the gap widen.

Single-shot chatbot
Tool-using agent

Illustrative. The point isn't the exact numbers — it's the shape: the harder the task, the more the loop matters.

The catch: acting is riskier than talking

When a chatbot is wrong, you get a bad sentence. When an agent is wrong, it can send the wrong email, update the wrong record, or spend real money. Autonomy raises the stakes, which is why the interesting engineering in agentic systems isn't the model — it's everything around it:

The mental model: a chatbot is an intern who can only talk. An agent is an intern who can also use your tools — which is far more valuable, and exactly why you'd never let them work without a clear scope, review, and an audit trail.

Key takeaways

Thinking about an agent?

We design agents that act on your systems safely — with the guardrails and evaluation to run them in production.

More insights

🛡️
Evaluation · 8 min

Evals are the product

🔒
Security · 6 min

Running AI fully on-prem

⚖️
Legal · 7 min

Human-in-the-loop by design