← Back to Autonomy
Agentic AI · Field Notes · No. 7 · By Majid Mazouchi

Don't build one super-agent.
Build a team.

A plain-language explanation of how multi-agent AI systems work — roles, feedback loops, and teamwork — with practical notes for putting it into production.

01

The big idea in one sentence

Core message

One agent that tries to do everything will do everything badly. A team of small, specialized agents — each with one clear job — does the work better, cheaper, and in a way you can actually debug.

Why does a single agent struggle? Because a complex task forces it to plan, fetch data, call tools, do the work, check the quality, and write the final answer — all in one breath, inside one crowded context window. Each extra responsibility makes every other responsibility worse. Mistakes pile up and nobody catches them, because the same model that made the mistake is the one "checking" it.

Human team analogy

You would never hire one person to be the architect, the developer, the tester, the researcher, the project manager, and the presenter on the same project. You create roles, give each person a clear scope, and let them hand work to each other.

The engineering name for this

This is simply separation of concerns, applied to AI. Each agent gets a narrow responsibility, a bounded context, and a measurable output. Smaller scope → fewer confusions → easier testing → easier debugging.

02

The seven roles on the team

The video describes a typical roster. You don't need all seven on day one — but it helps to know the full cast before you decide who to "hire."

P
Planner
thinks before anyone acts

In simple words: The planner reads the user's request and breaks it into a numbered list of steps before any work starts. "Build me a market report" becomes: identify the market → fetch data → compare competitors → analyze risks → make charts → write report → send for review.

Practical note

The planner's output should be a plan (a task list or task graph), never the work itself. If your planner starts writing the report, you've built it wrong. Give it a strong reasoning model — bad plans poison everything downstream.

D
Doer / Executor
produces the actual work

In simple words: The doer takes one step from the plan and executes it — writes the code, drafts the text, transforms the data. It's the worker on the assembly line. It's good at its small task, but it can't see the whole project, so its output may be locally right and globally inconsistent.

Practical note

Treat the doer like a worker node: hand it a precise task, its inputs, its constraints, and the exact output format you expect. Never let the doer own the workflow — that's how you get an agent quietly redefining the goal mid-task.

T
Tool Operator
hands on the real systems

In simple words: Language models don't actually know what's in your database right now. The tool operator is the agent that touches the real world: it calls APIs, queries databases, runs scripts, reads files, and brings back facts.

Practical note

This is your highest-risk role. Govern it with permissions, audit logs, read/write boundaries, and approval gates for anything destructive. And keep it dumb on purpose: it fetches structured evidence and returns it — it should not "reason freely" about what the evidence means, especially in safety-critical domains.

L
Learner / Researcher
keeps the team grounded

In simple words: The learner goes and finds outside information the team doesn't have — recent data, documents, announcements. In most real systems this is the RAG (retrieval-augmented generation) role: search a knowledge base, pull the relevant pieces, hand them over.

Practical note

The skill here is not retrieval — it's filtered retrieval. A good learner decides what is relevant, fresh, and trustworthy, and it labels where each fact came from. If you can, tag evidence by reliability (e.g. deterministic extraction > declared documentation > LLM inference) so downstream agents know what they can lean on.

C
Critic / Feedback Agent
the quality gate

In simple words: The critic reviews what the others produced and hunts for problems: hallucinations, missing requirements, logical contradictions, weak evidence, unsafe assumptions, bad formatting. This is the feedback loop that makes the team better than a single agent.

Practical note

A critic that just says "looks good" is useless. Force structured, actionable feedback: the issue, its severity, the evidence, and a recommended fix. Example: "The output references signal X, but X is not in the extracted interface. Severity: High. Fix: replace with confirmed signal Y or mark unresolved." In high-stakes systems, the critic is not optional — it is the safety layer.

S
Supervisor
runtime governance

In simple words: The supervisor watches the workflow while it runs. Are agents stuck in a loop? Did a tool call fail three times in a row? Is the budget blown? Should we retry, escalate to a human, or stop? The planner made the plan; the supervisor manages the execution.

Practical note

Watch for the classics: infinite loops, repeated failed tool calls, conflicting outputs, over-budget runs, low-confidence conclusions, and unsafe write actions. Give the supervisor hard STOP conditions. In production, this role becomes your runtime governance layer — the thing that keeps an autonomous system from quietly going off the rails.

Pr
Presenter
the final voice

In simple words: Internal agent chatter is messy. The presenter takes the validated results and assembles them into the thing the user actually sees — a clean report, an email, a dashboard, a document.

Practical note

One iron rule: the presenter formats, it never invents. If a fact didn't survive the critic, it doesn't appear in the final output. Pick a strong writing model here — this role decides whether your sophisticated pipeline looks sophisticated to the user.

03

How the team works together

A clean minimal workflow looks like an assembly line with one decision point. The supervisor sits at the gate: it accepts the work, sends it back for another pass, or escalates to a human.

USER REQUEST
Plannerbreak the request into steps
Tool Operator / Learnergather facts and evidence
Doerproduce the work product
Criticreview against the evidence
Supervisor decision
acceptretryescalate
Presenterassemble the final answer
FINAL ANSWER

Start small, grow only when needed

You almost never need all seven roles on day one. A sensible growth path:

The one failure mode to avoid

Do not let your main "reasoning agent" also be the retriever, the verifier, the planner, and the final writer. That single decision creates exactly the failure modes multi-agent design exists to prevent: hallucination, circular reasoning ("I checked my own work and I agree with myself"), hidden assumptions, and zero traceability.

04

Making each agent good at its job

Defining the roles is half the work. The video names four levers for making each role actually perform — and each one has a clean HR analogy.

4.1Prompting

= writing the job description

The system prompt defines the agent's role, its boundaries, its expected output format, and what to do when it fails. Vague prompts produce vague employees.

4.2Model selection

= hiring the right person

Not every role needs the same (expensive) model. Planner and critic want strong reasoning; the tool operator wants reliable function-calling; the presenter wants strong writing; the learner wants retrieval performance. Match the model to the job and you cut cost without cutting quality.

4.3Tuning & examples

= on-the-job training

Fine-tuning or just good few-shot examples make behavior consistent. A requirements critic, for example, learns fastest from examples of good requirements, unsupported claims, ambiguous references, and missing test procedures.

4.4Context

= the access policy

Each agent should receive only the context its job requires. Too much context confuses the model, raises cost, and increases hallucination risk. Context is need-to-know, not all-you-can-eat.

Prompting: the difference in practice

✗ Weak job description You are a helpful AI. Analyze this system.
✓ Real job description You are a Critic Agent. Your only job is to verify whether the generated requirement is supported by deterministic model evidence. Do not rewrite the requirement unless evidence is missing. Return PASS, FAIL, or NEEDS_REVIEW with cited evidence.
05

Mapping this to a real engineering system

The pattern becomes concrete when you map it onto a real domain — say, a knowledge engine for model-based automotive software (Simulink/TargetLink models, ARXML, A2L, requirement databases). The roles translate almost one-to-one:

Generic roleConcrete agent in an engineering knowledge system
Planner Decides the workflow per request: documentation generation, root-cause analysis, requirement tracing, or interface/ring analysis.
Tool Operator Deterministic extractors and query services — not LLMs. They parse MDL/SLX, ARXML, and A2L files, query the signal/ring/requirement databases and the vector store, and return structured evidence only.
Learner The retrieval agent: pulls supporting documents and context, and labels every fact by evidence level — DETERMINISTIC > DECLARATIVE > LLM_INFERRED.
Doer The domain-reasoning agent (e.g. motor-control reasoning). It reasons only after evidence has been retrieved — never from memory alone.
Critic The verifier: checks every generated requirement or conclusion against the evidence levels, flags unsupported signal references, and returns PASS / FAIL / NEEDS_REVIEW with citations.
Supervisor Controls retries, escalation to humans, missing-evidence handling, and hard STOP conditions for low-confidence or unsafe outcomes.
Presenter The formatting layer that writes the final deliverable — documentation blocks, system or unit requirements, or a root-cause report — using only verified facts.

Two design rules matter most in safety-relevant domains: extraction must be deterministic (parsers, not LLM guesses, decide what signals exist in a model), and the verifier is the safety layer — every LLM-generated claim passes through it before it reaches a human or a document.

06

Five things to remember

07

References & further reading

  1. IBM Technology. Building a Team of AI Agents: Roles, Feedback, & Teamwork Explained. YouTube, ≈10 min. youtube.com/watch?v=kqj22mWIdjU The primary source for this page: the seven roles and the four levers (prompting, model selection, tuning, context).
  2. IBM Think. What Are AI Agents? ibm.com/think/topics/ai-agents IBM's foundational definition of agents as systems that autonomously design workflows and use tools.
  3. Anthropic. Building Effective Agents. anthropic.com/research/building-effective-agents Strongly aligned advice: prefer simple, composable patterns; add agentic complexity only when the task demands it.
  4. LangChain / LangGraph documentation. Multi-Agent Systems. langchain-ai.github.io/langgraph/concepts/multi_agent Concrete implementation patterns for supervisor and hierarchical agent teams.