AI agents can work together in five ways: one after another, all at the same time, by passing the case to the right colleague, by discussing in turns, or under a manager who hands out the work. The way you choose matters as much as the agents themselves, because it decides who speaks to whom, in what order, and who has the last word.
This guide explains each of the five, with an everyday comparison, what it is good at, and where it goes wrong.
Why does the way of working matter?
Because a group of capable specialists is not yet a team.
Put five good people in a room without telling them who starts, who checks and who decides, and you get repeated work and contradictory answers. AI agents are no different. The same three agents can produce a clean result or a muddle, depending only on how they are organised.
The five ways below are the ones you choose from in the Agentivity Studio when you create a team.
The five at a glance
| Way of working | Like | Best for | Watch out for |
|---|---|---|---|
| Sequential | An assembly line | Steps that always come in the same order | One weak step spoils everything after it |
| Concurrent | Colleagues each taking a file | Independent tasks, when speed matters | Results that do not fit together |
| Handoff | A reception desk | Requests that must find the right specialist | Cases passed around without an owner |
| Group chat | A meeting | Questions that gain from being challenged | Long discussions that cost a lot |
| Manager-led | A project lead and a crew | Jobs where the steps depend on the request | A manager with a vague brief |
1. Sequential: one after another
Each agent finishes its part and passes the result to the next. Research, then draft, then review.
Like: an assembly line. Each station does one thing to what the previous one produced.
Good at: processes where the order never changes. It is predictable, and when the result is wrong you can see at which step it went wrong.
Watch out for: a mistake early in the chain travels all the way down. Put a checking step where an error would be expensive.
Example: a researcher gathers facts on a competitor, a writer turns them into a one-page note, a reviewer checks the note against the facts.
2. Concurrent: all at the same time
All the agents start together, each on its own part, and the results are gathered at the end.
Like: five colleagues who each take one file from the pile and meet again when they are done.
Good at: tasks that do not depend on each other. Reading five sources, checking a document against five rules, looking at one question from five angles. It is the fastest way to cover ground.
Watch out for: nobody sees what the others are doing while they work. If the parts need to agree with each other, add a member that puts them together and resolves the differences.
Example: one agent per store reads that store’s pages at the same moment, then the offers are compared.
3. Handoff: passing the case to the right colleague
An agent that receives a request it should not handle passes it to the colleague who should. You decide in advance who is allowed to pass a case to whom.
Like: a reception desk. You explain why you came, and you are sent to the right department, which may send you on if needed.
Good at: requests that arrive mixed. A customer message could be about a delivery, an invoice or a technical fault, and each needs a different specialist.
Watch out for: a case that keeps being passed along. Give every case a clear owner, and limit who can hand over to whom.
Example: a first agent reads each incoming request and sends it to billing, delivery or technical support.
4. Group chat: a discussion in turns
The agents speak in rounds, and every one of them sees everything that was said. Each reacts to the others.
Like: a meeting where everyone hears everyone.
Good at: questions with no single right answer, where being challenged improves the result. Reviewing a plan, weighing a decision, improving a piece of writing.
Watch out for: meetings can run long. More rounds mean more calls to AI models, so more time and cost. Decide how the discussion ends: a number of rounds, or one member who concludes.
Example: a strategist proposes a campaign, a finance specialist challenges the budget, a brand specialist checks the tone, and they go round until the plan holds.
5. Manager-led: a manager hands out the work
A manager reads the request, decides what needs to be done and by whom, hands out the work, and assembles the answers. The specialists can work at the same time.
Like: a project lead with a crew. The lead does not do the work, but knows who should.
Good at: jobs where no two requests need exactly the same steps. The manager adapts the plan to each request, and calls only on the specialists it needs.
Watch out for: everything rests on the manager’s brief. If its role is vague, it will hand out work badly. Describe carefully what each specialist is for.
Example: the Trip Planner team has a manager and twelve specialists. A weekend away and a month abroad do not call on the same ones.
How do you choose?
Answer three questions about the job.
Do the steps always come in the same order? If yes, go sequential. If the order depends on the request, look at manager-led or handoff.
Do the parts depend on each other? If not, run them concurrently and save time. If they do, they must happen in order, or be discussed.
Is there one right answer, or does the answer gain from debate? If debate helps, use a group chat, with a clear way to end it.
When two ways seem to fit, pick the simpler one. You can change later: the members keep their roles, and only the organisation changes.
Can you combine them?
Yes, and real teams often do. A member of a team can itself be a team.
A manager can hand “write the report” to a small sequential team of writer and reviewer, and “check the sources” to three agents working concurrently. Each part of the job gets the organisation that suits it.
Start simple all the same. A team of three working sequentially teaches you more about your job than a large structure you cannot follow.
Where do people fit in?
In all five. Whatever the way of working, a team should stop and ask when a decision belongs to a person: approving a rejection, choosing between two options, confirming a payment. Where those stops go is a separate decision, covered in where a person should stay in charge.
In short
Choose sequential for a fixed chain, concurrent for independent tasks, handoff to route requests, group chat when debate helps, and manager-led when each request needs its own plan. If you are new to the idea of AI specialists working as a team, read what a multi-agent system is first, then see a team being built.
Questions people ask
Which way of working should I start with?
Sequential. One agent after another is the easiest to follow and to correct. Move to another way of working when you can name what sequential does badly for your job.
Can I change the way of working later?
Yes. The members keep their roles. You change how they collaborate, then run the team again on the same cases and compare.
Can a team contain another team?
Yes. A member of a team can itself be a team, so a manager can hand a part of the job to a small group that works sequentially, for example.
Which way of working costs the least?
Usually sequential, because each member works once. Group chat and manager-led involve more exchanges between members, so more calls to AI models. The right choice is the cheapest one that does the job well.
Do I need to code to set this up?
No. In the Agentivity Studio you choose the way of working from a list when you create the team, then you drag the members in.