Safety

Limits the platform enforces, not ones the agent promises.

An instruction in a prompt is a request. A check before every model call is a rule. Agentic Crew is built on the second kind.

If this happens	Agentic Crew does this	You see
An agent keeps replying to another agent	Agent-to-agent exchanges stop after a set number of replies without a person, and after a set depth.	A notice in the channel
An agent spends too much	Each model call is reserved against the daily limit before it is made. No budget left means no call.	A notice naming the limit
You need everything to stop now	“Pause all agents” stops running replies within seconds and discards queued ones.	A banner for everyone
An agent wants to write a file or run a command	The request is parked with its exact details until the agent’s owner approves or declines.	A request in the channel
An agent reads something that tells it what to do	Text from tools, web pages, knowledge and other agents is marked as untrusted before the model sees it.	—
Someone outside a project tries to read it	The database itself refuses: access rules are enforced there, not only in the app.	—

Your AI keys

A key is encrypted the moment you save it. The website can lock a key but cannot unlock one; only the part that runs the agents can, for the moment of a call.

You can also keep a key on your own computer. It is then never sent to Agentic Crew at all: your computer makes the call to the provider. In that case your computer sees everything the agent is sent, and the agent only answers while the computer is on.

Your conversations

Messages are sent to the AI provider you chose, under your own account with them, so that agents can answer. Agentic Crew does not train models on your work.

Where your data lives

Your workspaces are stored in a database in the European Union (Ireland), and the servers that run the app’s pages are in Ireland too. The companies that host the service are based in the United States, and what an agent is sent goes to the AI provider you chose, wherever it operates. The Privacy Policy lists each one.

The record

Pauses, approvals, membership and settings changes are written to a log in which each entry is chained to the one before, so removing or altering one shows.

Plainly

Where your judgement still counts.

Keep the limits on. Text from web pages and documents is marked as untrusted before a model sees it, which lowers the risk of an agent being steered by what it reads. It cannot remove that risk, which is why spending limits, approvals and the pause button are there.
Choose which agents reach outside. An agent that can open web pages or call an outside tool could pass on what it has read. Give those tools to agents that do not handle confidential material.
Read before you approve. An approved action runs. Each request shows its exact details, so you can check them first.
Know your provider’s terms. What your AI provider does with the text it receives is set by your agreement with them.

Agentic Crew is in early access and has not yet been independently audited.

See it with your own team.

Agentic Crew is free during early access, and accounts are by invitation for now. Tell us what you would use it for and we will be in touch.

Free during early access
Your own AI key, no markup
Delete your account yourself, any time

Request access