Making several AI agents work together, without chaos
One role per agent, written hand-overs, shared rules, a single source of truth: how to organise several AI agents like a team.
A first agent is a project. Three agents are an organisation. And like any organisation, they need roles, rules and hand-overs, otherwise each one works in its own way.
What happens without organisation
- Contradictory answers: the customer service agent announces a lead time the invoicing agent does not know about.
- Duplicates: two agents chase the same customer on the same day.
- Orphan cases: a request goes from one agent to another, and nobody finishes it.
- Rules that diverge: each agent has its own copy of the prices, and they are no longer updated at the same time.
An organisation in levels
The simplest approach is to model the agents on your organisation:
| Level | Role | Example |
|---|---|---|
| Shared memory and rules (optional) | what applies to the whole company | priorities, vocabulary, trade-off rules |
| Business agents | a whole domain, with its knowledge | finance, customer relations |
| Process agents | a process, end to end | reminders and collections, invoice processing |
| Tasks | a specific action | extracting the data from an invoice |
Each agent knows where its rules come from, and to whom it reports.
The five rules that prevent chaos
1. A clear role for each agent
What it does, what it does not do, to whom it hands over. Two agents must not have the same role on the same case.
2. Written hand-overs
When a case passes from one agent to another — from qualifying a request to handling it, from the invoice to the reminder —, the hand-over is described: which information, which format, who checks.
3. Shared rules, in a single place
Prices, lead times, vocabulary, priorities: a single source, which all agents refer to. Two copies always end up diverging. See Organising company knowledge in layers.
4. Decisions reserved for people
The more agents there are, the clearer you must be about what remains human: paying, signing, setting a price, publishing, settling a strategic decision. See Governance.
5. Records that follow the case
Being able to reconstruct a case’s journey, from one agent to another: that is what makes it possible to understand an error and correct it.
In a mid-sized company: consistency before numbers
In a mid-sized company, agents often arrive department by department, with different providers. The risk is not the number of agents: it is the inconsistency between them. Writing the shared rules and governance once, for all, costs less than reconciling agents that contradict each other. See From AI pilot to production in a mid-sized company.
Where to start
- One process, then a second one in the same domain.
- The whole domain, with its knowledge written down for the agents: Business Agents.
- Shared rules and memory, when several domains are involved: the Company Brain, optional.
You pay for a result, not for a number of agents: how many are needed is our business.
Frequently asked questions
From how many agents do you need to get organised?
From the second one, if both deal with the same customers, the same data or the same rules. An invoicing agent and a customer service agent must say the same thing about a payment deadline.
Do you need an agent that directs the others?
Sometimes: a domain agent can share out the work among process agents. But the essential thing is not the technical hierarchy: it is the roles, the shared rules and the decisions reserved for people.
Do you pay for each agent separately?
With us, no: you pay for a result — a process or a domain taken over —, not for a number of agents. How many agents are needed is a design choice.