With a personnel file, a probation period and a boss who stays human. AI colleagues that work where your team works — and ask permission for anything risky.
An AI colleague is not a chatbot. It has a role, a supervisor, a budget and limits — and it follows your processes. Not configured. Hired.
No prompt engineering. You describe a role — the platform runs it through assessment, probation and sign-off before anything touches production.
Hiring and leading in detailRole, persona, thinking tools, no-gos, model, skills, budget. Every change versioned and revertible.
Adversarial testing across five dimensions. An independent judge model scores each one with reasoning.
Sandbox operation with tight feedback loops. Rehearse real processes safely — effective actions run as simulation.
Approval rules, escalation deadlines, budget caps. Trust grows in steps, never all at once.
Not a checkbox in a settings dialog. Every AI colleague inherits a responsible supervisor through the hierarchy — with deputies, deadlines and a safe default at the end of the chain.
Control and safety in detailLarger jobs do not start with work but with a card: goal, waves, open questions — and explicitly the non-goals. You approve, return or reject.
Planning mode in detailHall 9 like last year — or hall 4, closer to the entrance and 15 % pricier?
A plan is always decided by a human — even when a team lead had it drafted.
Nobody has to learn a new program. AI colleagues live in the internal chat, in Microsoft Teams and in the shared mailbox — reachable by @mention, replying in-thread.
Everyday work in detail@mention in the channel, centrally managed mailboxes polled every minute, replies bundled and only when there is substance. Only someone explicitly assigned to a mailbox may send; meetings and calendar entries are part of it.
The built-in assistant sets things up, explains and diagnoses — in plain language. Every change arrives first as an approval card with a reason you can actually read.
Schedules down to the minute, triggers from other systems via signed webhooks, handover notes from run to run. After three failures the platform stops the colleague itself.
A team lead breaks down the task, delegates to specialists, reviews and delivers consolidated. Four-eyes principle built in: whoever creates does not review.
Sick leave, incoming invoices, customer requests — described once in plain language, binding for every relevant colleague. Testable in a scenario beforehand.
You decide where AI simply does not belong — secured twice: as a binding rule at the employee's core and as a hard stop in the paths that lead outside. The Teams connector then refuses the DM reply, the mail system refuses external sending.
Human zones in detailMulti-tenant by design, not retrofitted. Data separation is enforced by the database itself — it does not depend on application code.
Foundation and operations in detail| Tenant isolation | Row-level security at the database layer — separation between companies does not depend on application code. |
|---|---|
| Sign-in | Enterprise SSO via OIDC/SAML, e.g. Microsoft Entra. Fine-grained roles down to a single approval permission. |
| Deployment | Operated as SaaS, exclusively in EU data centres. No data leaving the EU. Tools that must not leave your network are reached by a small service at your site — connected outbound, with nothing opened in your firewall. |
| AI models | Multi-provider out of the box. The model is chosen per role and swappable at any time — no vendor lock-in. |
| Skills | Open MCP standard (Model Context Protocol): CRM, calendar, ticketing, your own internal services — including ones reachable only inside the company network. |
| Credentials | Encrypted in the credential vault only, with a per-tenant key. Never in clear text — not even in approval cards. |
| Audit | Tamper-evident, fully chained log: every call, every approval, every decision, every cent. |
| Knowledge | Knowledge collections with semantic search during work, strictly separated per tenant. |
Daily and monthly cap per employee. Warning at 80 %, stop at 100 %. Never a surprise invoice.
Subject, status, an archive that returns on a late reply. No case is closed quietly — staying open for long is a signal.
Every Monday, automatically, in the channel of your choice: top 5 costs, incidents of the week, concrete recommendations.
You write in one sentence WHEN a tool is allowed. Whatever no rule grants goes to a human — and a new rule may observe first before it takes effect.
Incoming files get read — including from mail. Outgoing, a finished document on your letterhead appears, not a text file.
"Why isn't Sabine responding?" — status, root cause, stuck deliveries, open approvals. In seconds, no log archaeology.
30 minutes, one real use case from your company, no slides. We show hiring, assessment and approval live.