AI agents as a team: nothing goes out without human approval
One AI agent is useful, but several need organising: who does what, who may send, and what counts as approval. Every one of our agents follows these rules.
the problem
When a small team uses several agents, small but awkward mistakes show up quickly:
- two agents write a draft of the same message on the same thread,
- the same notification arrives twice,
- a passing idea or a misread “let’s start” looks like approval,
- a confidential internal report ends up among the material that goes out.
our rules
- Nothing goes out without explicit human approval. This covers email, messages, posts, applications, payments and changes made on a machine.
- Only a human’s approval counts. Another agent’s “approval” does not, and neither does “let’s start”: that opens a conversation, it is not a permission.
- The human sees the full text before sending. After an edit, a new approval is needed.
- We check before sending. We look for an existing draft of the same message and tell the teammate agent, so nothing goes out twice.
- One task has one owner. For example, one agent writes a referral and another sends it after approval. The coordinator hands bigger work to specialised assistants.
- Confidential material is kept apart from what goes out. Partner identifiers are masked in external material.
- We keep a record. We note what we have already flagged and what the learned preference is, so we do not say it twice and do not ask again.
- On external profiles we only read, and we never guess personal contact details.
who does what
| task | the agent | the human |
|---|---|---|
| outreach, letter, post | writes it and shows the full text | approves it and decides on sending |
| request for quotation, partner letter | drafts it and checks that no such draft exists | authorises it with an explicit yes |
| referrals to companies, candidate data | one agent writes, another sends | approves before sending |
| website, webshop | builds it and tests it on several sizes | decides on steps involving money, accounts and customer-facing text |
| video, creative material | delivers a new version each round | approves style, images and cut, and publishes |
| analysis, report, decision table | assembles it as a draft, with a recommendation | decides the next step |
what we gain
- With one coordinator agent, several parallel projects can be steered from a phone with a few words.
- Not one deadline was missed, while the time spent on daily email handling fell to a fraction.
- Multi-source technical work takes hours instead of days, and a human checks every step that has an effect outside.
general lessons
- We state the limits first, and ask early about the purpose, the format and the visual expectations.
- It is better to start with one striking, easily understood function and to agree on the vision before building.
- We read AI suggestions critically. For web sources we check the date and the primary source, and we flag uncertainty openly.
- We check platform limits in advance, and we deliberately leave key decisions to the human.
want something similar?
If you want to work with agents while every step that goes out stays in your hands, talk to oiSystem.