PSG Polytechnic · 11 August 2026 · a 101

AI, Agents,
and Multi-Agent Systems

Three words you will keep hearing · what each one actually means, and when you need it

Siddarth Kengadaran Experience Strategist

The Whole Hour, In One Picture

Three Words, In Order

Each one is the previous one plus a single new idea. That is the entire progression.

1 · AI MODEL TEXT IN, TEXT OUT 2 · AGENT TOOLS MODEL IT PICKS ITS OWN NEXT STEP 3 · MULTI-AGENT SHARED SEVERAL, ON ONE STORE

Why · 8 min

Why You Are Being Taught This

Why

The Word Will Be On Your First Job Description

You are going to be asked to build an “AI agent” before anyone explains what one is. The word is doing a lot of work in job posts and almost none of it is precise.

So this hour is not about a framework or a vendor. It is about the three ideas underneath all of them, which will still be true after the tool names change.

You do not need to have written much code to follow this. If you have used a chatbot, you have used the first of the three.

Part 1 · 10 min

AI: The Model

What It Is

A Model Is a Function

Text goes in. Text comes out. That is the whole contract.

ONE TURN ASK MODEL ANSWER

It has read a great deal and it is very good at continuing a sentence. It is not connected to anything. It cannot see your files, your database, or today’s date unless you paste them in.

What It Cannot Do

Two Things Are Missing

Both of them matter more than how clever the model is.

It cannot reach

Ask it about your college timetable and it will tell you, correctly, that it has no access. Being right about what it cannot see is not the same as being useful.

It cannot take a second step

One question, one answer, finished. It cannot look something up and then decide what to do about it.

Fix those two and you have not built a smarter model. You have built an agent.

Part 2 · 15 min

Agent: The Loop

What An Agent Is

Three Ingredients, Nothing Else

Follow the arrows. Each ingredient has a place in the picture.

TOOLS reaches past its own context FROM YOU TASK THINK ACT OBSERVE GOAL MET? YES ANSWER NOT YET A LOOP — IT GOES AGAIN

Tools

A search, a database, a calculator. Now it can reach.

A loop

It goes round again with what it just learned.

A goal

It decides when it is done. You did not write that stopping point.

The Test

One Question Tells You Which Is Which

Who picks the next step?

ONE TURN ASK MODEL ANSWER

Plain call

Nobody. There is no next step.

YOU WROTE THIS ORDER STEP 1 STEP 2 STEP 3

Workflow

You do, in code. You knew the order before it ran.

NOT KNOWN IN ADVANCE STEP STEP STEP

Agent

The model does, as it runs, based on what it finds.

Write this one down. It sorts every system you will ever be shown, whatever it is called.

The Part Nobody Says

Most Things Should Not Be an Agent

If you can write the steps down, write them down. A for loop is cheaper, faster, easier to debug, and it will not invent a fourth step at two in the morning.

Use an agent when the next step depends on what you find. If you cannot name a step that changes based on the answer to the one before it, you want a workflow.

That flexibility is what you are buying. The rest of this hour is what it costs.

How

Build Your First One This Week

01

Get a free key from Google AI Studio. No card, no cloud project.

02

Send one question to the model and print the answer. That is the whole of step one, and it is worth doing on its own.

03

Give it exactly one tool — a function it can call. A search, or even just a list of your files.

04

Write the loop by hand: ask, let it call the tool, feed the result back, ask again. Do not reach for a framework yet.

Write the loop once yourself and every framework afterwards is just packaging you can already read.

Part 3 · 18 min

Multi-Agent: The Wiring

Why A Second One

Three Honest Reasons

One agent with tools already does a lot. So why add another?

Separate context

One reads fifty documents and passes on a page. The next never carries the fifty.

Separate permissions

The one that reads the database should not be the one that sends email.

Parallelism

Ten independent files, ten agents, one wall clock.

Notice what is missing: “so each one can specialise in a role.” That is the reason most people give, and it is the weakest one.

What Everyone Builds

The Obvious Thing

A hard task goes to one agent. It does a mediocre job. So you hire it a team.

BRIEF DRAFT REVIEW TASK RESEARCHER WRITER CRITIC MANAGER ANSWER EVERY ARROW IS PROSE, AND EVERY ARROW REPACKAGES THE CONTEXT

Four agents. On the run behind this talk it cost about five times the tokens and five times the wait — and the answer was no better than the single agent’s.

Why It Gets Worse

You Rebuilt a Group Project

Every arrow is a place where the task gets retold in someone else’s words. The task survives. The understanding of it does not.

Brooks wrote this down in 1975 about people: adding more of them to a late project makes it later, because the lines between them grow faster than they do.

Agents are worse than people here, for one reason: they never say “wait, I don’t follow.”

What It Looks Like

On a stronger model the same chain cost eleven times a single agent, and when asked for three sentences it produced eighteen.

Nobody wrote anything wrong. The instruction was four handoffs back, and each agent was answering the one in front of it.

1 AGENT · 0 PATHS 2 · 1 PATH 3 · 3 PATHS 4 · 6 PATHS

Where The Cost Is

The problem is not the model, and it is not how many agents you have. It is what it costs to carry the task across a gap.

THE BOUNDARY AGENT A AGENT B … OR A HUMAN, OR THE NEXT RUN HANDOFF COMPRESSION DRIFT VERIFICATION TOKENS GOVERNANCE

Every boundary charges you something. A bigger model pays the same tolls.

How To Fix It

Stop Passing Prose

The same handoff, done two ways. Follow what happens to the original note.

PROSE HANDOFF PROSE PROSE PROSE NOTE BRIEF DRAFT ANSWER THE SOURCE IS GONE AFTER THE FIRST HOP TYPED HANDOFF SCHEMA SCHEMA SCHEMA NOTE CLAIM + QUOTE CLAIM + QUOTE ANSWER THE ANSWER STILL POINTS BACK AT THE SOURCE

Make each agent hand on a claim with the quote it came from, instead of a paragraph in its own words. Now you can check the answer without trusting anybody.

Five Shapes

How You Wire Them Beats How Many

BOARD

Blackboard

Agents read and write a common evidence store.

Prefer
POLICY

Adaptive

A policy picks the structure per task.

Best

Committee

Agents argue to consensus in free text.

Worst

Hierarchy

A manager agent routes the work.

Lossy

Rigid pipeline

A fixed sequence, every time.

Brittle

The bottom three are agents imitating a human meeting. That imitation is what you pay for.

The Counterintuitive One

Five Hats, One Head

Before you add an agent, ask one thing: can it be wrong in a way the others cannot?

Keep it

A different model, a different tool, or a different source of evidence.

It can catch what the others structurally cannot. That is real signal.

Cut it

The same model with a reworded prompt and a different job title.

Three agents built this way agree with each other because they are the same agent. You paid three times for one opinion.

Part 4 · 7 min

What Doesn't Change

The Part That Is Not New

The Machine Cannot Do These

Everything so far was systems. This part was never about the tools.

Intent

You did it on purpose and you can say why.

Curiosity

You want to know how it works, not only that it worked.

Honesty about the work

You don’t cut the corner nobody would ever see.

Sitting with ambiguity

You can hold a problem open before closing it.

A course can teach you methods. It cannot make you any of these, and neither can the machine: it takes instruction rather than intent, and it cannot sit in ambiguity — it resolves to the average, every time.

Take It With You

Four Things Worth Keeping

Ask who picks the next stepNobody, you, or the model. That sorts every system you will be shown.
Most things are not agentsIf you can write the steps down, write them down.
Wiring beats headcountOne shared store beats four agents retelling each other the task.
Carry the evidenceA claim with its quote can be checked. A paragraph cannot.

Build the smallest thing you can actually explain. Make it bigger only when something forces you to.

The working notebook. Every idea in this deck, as code you can run on a free AI Studio key.

colab.research.google.com/drive/1brSW2oJTzEi4_0bd2698pYjEQVsEfJSr?usp=sharing

theproductguy.xyz /two-speed-engine