Back

How an AI agent actually works, in five pictures

The version I wish someone had drawn for me before I started building these for health and wellness practices.

Aug 2026 · Rincón, PR

Most people picture a chatbot. You type, it types back, and nothing in the world changes. An agent is the other thing. It reads a situation, decides what to do about it, does it in real software, and then tells you what it did. The typing is the smallest part.

ChatbotYou ask?It answersAgentYou ask?BooksFilesReplies
Same question. One of them ends in words, the other ends in something moved.

It runs in a loop

An agent is not one answer. It is a small loop that keeps going until the job is done or until it gets stuck. Read what came in. Decide what to do. Do it. Check whether it worked. Say what happened. Then round again with whatever is left.

ReadDecideDoCheckReport
Round and round until the job is finished, or until it is honest about being stuck.

The last two steps are where the value is. Anything can do something. Checking the result and admitting when it went wrong is what makes an agent safe to leave running.

What one is made of

Four parts, and only four. Instructions are what you want and how you want it done. Tools are the things it is allowed to touch: a calendar, a form, a message queue. Memory is what it knows about this person and this practice. Limits are the edges, the things it may never do without asking.

InstructionsToolsMemoryLimitsAgent
Everyone wants to talk about the first three. The fourth is the one that decides whether it survives a month.

Where it fits in a practice

Not the care. Never the care. Agents belong on the repetitive edges of a week, the jobs that are the same every time and that nobody enjoys.

  • Turning a new enquiry into a booked appointment
  • Chasing the intake form somebody started and abandoned
  • Reminding, rescheduling, and following up after a visit
  • Writing the boring half of a record so a person can write the half that matters

Each of those is one narrow job with a clear finish line. That is the shape that works. An agent asked to run the front desk in general will run it badly.

The dial that decides everything

Every agent has one setting: how much it is allowed to decide on its own. Turn it up and it saves more time. Turn it up further and you start spending your evenings undoing what it decided. The two lines cross somewhere, and the whole job is finding where.

the useful settingTime it saves youTime you spend fixing itlessmoreHow much it decides alone
The shape of it, drawn from my own work rather than measured data. Where the lines cross depends entirely on the practice.

The agents that last do one narrow thing, write down what they did, and hand control back the moment they are unsure.

What stays human

Before I build anything, I sort every task in a practice into three piles.

The agent finishes itroutine, reversible, loggedThe agent drafts it, a person sends itanything with a voice attachedA person, alwaysanything clinical, anything about money, anything about someone's body
The bottom pile is not a limitation to engineer around. It is the reason the top pile is allowed to exist.

If you want to start

Pick the single job that annoys you most this week. Make sure it is reversible and that you would notice if it went wrong. Give the agent that one job, make it write down everything it did, and read the log for two weeks. Then decide whether it gets a second job.

The agent that survives is boring. It does one thing, leaves a trail, and hands back control the moment it is unsure. Nobody writes a case study about that, which is exactly why it keeps working after you stop watching.

Shaun Duval