Agentic AI Chapter 12 / 16 · Multi-Agent

12 Multi-Agent Systems

When one agent
isn't enough.

A single agent is capable, but it has real limits. On a long task its context window fills up. It can't be a deep expert at everything at once. And doing things one step at a time is slow. Multi-agent systems answer all three: several specialized agents work together — in parallel, checking each other's work — the way a team beats a lone generalist.

Sequential Parallel Hierarchical Debate

Why teams beat soloists

The limits of one agent.

Every problem in this chapter comes from asking a single agent to do too much. Name the limit and the fix becomes obvious: split the work across a team.

The context fills up

An agent can only hold so much in its working memory. On a long, sprawling task, early details get pushed out and the agent starts to lose the thread — like trying to keep an entire novel in your head at once.

No single expert

One prompt can't make an agent world-class at research and writing and code review. Ask it to be everything and it's mediocre at all of it. Specialists, each with a sharp focus, go deeper.

One thing at a time

A lone agent works in a line: finish A, then B, then C. If three parts don't depend on each other, doing them one by one is just wasted time. A team does them at once.

The gallery

Four ways to arrange agents.

Once you have more than one agent, the real question is how they're wired together. There are four core shapes — each moves work and information differently. Pick one to see its topology and where it fits.

Researcher Writer Editor Publisher each agent's output is the next one's input
Input Worker 1 Worker 2 Worker 3 Aggregator
Orchestrator Specialist 1 Specialist 2 Specialist 3 delegate report back
Agent A Agent B Judge proposes critiques A revises picks best

an assembly line

Sequential

Best for
Watch out for
Same kind of agent in every box — you're choosing how they pass work and check each other.
The pattern most production systems reach for

Hierarchical. A manager agent breaks the job into pieces, hands each to a specialist, and stitches the results back together. It's flexible enough for messy real work and keeps any one agent's context small — which is exactly why it's the workhorse.

Putting it together

A real production example.

Picture a team of agents building a piece of software. No single agent could hold the whole job in its head — but a hierarchy of specialists can, because each one only worries about its own slice.

Orchestrator
Runs the show. Reads the goal, splits it into tasks, hands each to the right specialist, and assembles the finished result — the manager at the top of the hierarchy.
Architect
Designs the overall structure and decides how the pieces fit together — before a line of code is written.
Coder agents ×3
Implement separate components in parallel — independent pieces built at the same time, not one after another.
Test agent
Writes and runs tests against what the coders produced, catching what slipped through.
Review agent
Reads the code with fresh eyes for quality and bugs — a second opinion the author can't give themselves.
Docs agent
Writes the documentation so the work is usable by the humans who come next.
The quiet superpower

Notice that the Test and Review agents exist only to check other agents' work. A lone agent grading its own homework tends to miss its own mistakes. A separate reviewer, with no ego in the code, catches them — and that cross-checking is what makes a team more trustworthy than any single agent.

Chapter 12 key idea

Specialized agents that check each other beat one generalist trying to do everything — deeper focus, work done in parallel, and a second set of eyes. That's why the hierarchical manager-worker shape is the workhorse of real production systems.

Chapter 12 in one breath

Many small experts, wired together.

One agent runs out of context, can't be expert at everything, and works one step at a time. A team fixes all three. Wire them in a line to pass work along, in parallel to do independent pieces at once, in a hierarchy so a manager delegates to specialists, or in a debate so they sharpen each other. Hierarchical is the one you'll reach for most. Next: the frameworks that make building these teams practical.

🖥 Present this chapter

A matching slide deck with speaker notes — press S for notes, F for fullscreen.

Open the slides →