The human layer for AI agents
Give AI tools and agents a governed way to ask people for decisions, and to deliver the reports, dashboards and briefings they produce to the people who need them.
Flow
An agent asks for approval, a review, an answer or a decision. A person answers on a page that works on a phone, and the agent carries on with what they said.
Reports
One address you send once. Publishing again puts a new version behind the same link and keeps every earlier one, and each open is checked against who may read it.
What you get
The person approves, rejects, answers or asks the agent a question back — and the agent receives it.
An administrator writes them; the agent does not. Most calls settle without interrupting anybody, and every one is recorded.
An agent acts as itself, inside boundaries somebody set, rather than borrowing a person's credentials.
A persistent address with version history, rollback, and a refusal when two publishes race.
Every open is checked against identity and the audience the report was published to, so a forwarded link forwards nothing.
Who asked, who decided, what they saw, what changed and who opened it — kept as a tamper-evident record you can export.