Call your systems.Or let them call you.
An AI assistant on the phone with access to your own systems. It keeps your appointments, makes new ones and schedules them, reminds you at the right moment and calls you at a fixed time with a briefing. You pass on tasks while you drive, and it asks for hours and kilometres so you never have to fill them in afterwards.
It ran at our place first.
During the day we are often at a client or at the university, and Aether runs in between. Sitting down at a screen to fill in hours or check how a project is doing simply did not happen. Now a voice assistant calls every working day at half past five with the state of affairs, takes on tasks and asks about hours and travel costs. The call report is in the log ten minutes later.
Does this sound familiar?
- 01You are on the road, and everything you need to pass on sits behind a login screen.
- 02Hours and kilometres are reconstructed at the end of the month, and therefore too low.
- 03An idea or appointment from the car is forgotten by the time you get home.
- 04Reading an overview takes attention you do not have during the day.
What you get.
- A phone number of its own for your assistant, with an access code before it tells you anything
- Keeping appointments, making and scheduling new ones, and reminders at the right moment
- A daily call with a briefing from your own systems
- Passing on tasks, notes, hours and kilometres in plain speech
- A call report that lands in your file or CRM automatically
- Fixed boundaries: which systems it may read, what it must never do
- Honest advice on where to use it: in our experience voice AI is not yet good enough for conversations with customers, for internal use it already comes in handy today
- More uses than these: which conversations a digital secretary could take over at your place, we explore together
Operating it yourself says more than a description.
Play a sample call and watch alongside what happens in the systems: an appointment being scheduled, a reminder, hours and kilometres being logged. This is a demo on sample data, not client work.
Demo · prepared in advance · illustrative · no live model
Not played yet. The secretary calls you at a fixed moment; play the call to follow along.
Once the call is running, what gets recorded appears here.
Limits: may read your calendar, mail and time registration, sends nothing without your confirmation.
Illustrative demonstration with examples prepared in advance. No live AI call and no API key needed; the answers are fixed and contain no invented figures or names.
Four steps, in this order.
We sit in
We look at which information you miss on the road and what you now fill in afterwards, and decide together what the assistant may access.
We build alongside
The first version runs separately from your systems and writes nothing into them. If you stop, nothing has changed.
You keep the last step
Whatever the system produces is first ready as a draft. Only when you give the go-ahead does anything leave the building.
We connect only once it works
Once it proves right in practice, and only then, we connect it to your systems for good.
Lead time: one to three weeks for a working first version.
ElevenLabs · Telephony · Custom tools on your systems · Python · Anthropic
What people ask us about this.
Q1Can it talk to my customers too?
Technically yes, but in our experience voice AI is not good enough for that yet: a customer notices the difference and drops out at the first misunderstanding. For internal use, with yourself or your team on the line, it already works well.
Q2What if someone else calls the number?
Before the assistant tells anything, it asks for an access code. Without the code the caller hears nothing from your systems.
Q3Can it do things in my systems by itself?
Only what we agree beforehand. Scheduling an appointment or logging hours is possible; sending email or deleting something it does not do without your confirmation. Those boundaries are fixed in the technology, not in an instruction.