Draft, never decide
The assistant prepares; people approve, reject and release.
An assistant that prepares work in every hub; a person always decides.
AI is the assistant built into every hub. It answers questions, drafts records, configures screens from plain language and plans multi-step tasks, always as the signed-in person and within their rights. Money, approvals and other sensitive decisions stay with people, and administrators control what AI may do, which models it uses and how much it can spend.
The assistant prepares; people approve, reject and release.
Hide a field or add a column in plain words with one-step undo.
Kill switches halt one agent or all AI for a tenant.
Allowance, alerts and prepaid credits keep AI costs bounded.
Autonomy, fields, providers and regions are set by you.
Search or filter. Planned items are labelled; everything else is available now.
Ask, find, draft and act from the screen you are on.
12 featuresTell AI how you want a screen or a setup to look.
7 featuresAsk for several things at once; review the plan; confirm.
7 featuresAdministrators decide what AI may do, per hub, role and user.
10 featuresTreat every non-human caller as a registered agent you can stop.
7 featuresPredictable spend with no surprise bills.
6 featuresRecognise people who configure AI well.
2 featuresIt prepares the work. A person confirms it.
The same four building blocks, specific to boss AI.
AI can draft policies and automations but cannot approve, reject, delegate or publish; agent approvals by risk tier go through workflow.
AI usage, spend and agent activity are available as governed datasets.
Datasets
Dashboards
External AI tools connect over MCP and the admin MCP under the same policy.
/v1 AI usage and agent resources; /mcp and /mcp/admin
Connectors
Migration includes an AI pack drafter that proposes connector packs for a person to approve.
The phone frame has an AI tab; the same assistant answers there. Voice is planned.
No. Approvals, rejections, publishing, releasing and money movement are person-only.
The signed-in person's. It never has more access than they do.
Yes. AI can be off for the tenant, a hub, a role or a field, and there is a kill switch.
Administrators can restrict providers and regions, or add their own key.
By default the assistant pauses and tells people; top-ups can be enabled.
Yes, personally with undo, or for the company with a preview and confirmation.
The design aims for no training on tenant data; confirm with your agreement.