Questions people ask before a quick-check.
If yours is not here, it is a good reason to book the thirty minutes. We answer everything in writing afterwards.
What exactly is an AI agent?
Software that reads what arrives (an email, a call, a document, a set of numbers), does the repetitive part according to rules you set, and hands anything it is unsure about to a person with the facts already gathered. Unlike a chatbot, it acts: it books, files, drafts, matches, reports.
Does our data leave the company?
No. Agents run inside your existing tools and your own accounts. Where a model is needed we use EU-hosted options by default, and nothing is used to train anyone’s model. We document the data flows for your GDPR register before we start.
Which tools do you work with?
Whatever you already use: Microsoft 365 or Google Workspace, your phone system, your CRM, your accounting or practice software, your booking system, your document templates. We do not ask you to switch.
How long until something actually works?
A quick-check is a 30-minute call. The first working prototype on your real data takes two weeks. Most teams have something running in their week within two months.
How much does it cost?
Each step has a fixed price agreed before it starts: the quick-check is free, the two-week prototype and the build are quoted in the note, and the run step is a monthly amount you can cancel. We do not publish a price list because the right scope depends on your volume and tools; the note gives you the exact figures.
What if it gets something wrong?
Every agent starts read-only, drafts before it sends, and hands anything it is unsure about to a person. It only acts alone in categories where you have seen it be right, every action is logged, and any category can be pulled back to draft mode in a minute.
Who builds it, and who do we call?
A small team, with the founder in every project. You have one person accountable from the first conversation to the system running, and a phone number that is answered.
Do you work in French?
Yes. We work in French and English, on site in Monaco and the Riviera or remotely anywhere, and the agents answer your clients in their language, including Italian, German and others.
Who owns the code?
You do. Source, data and documentation are handed over at the end of the build. You can run it yourself, give it to your IT, or keep us for the run step.
Will this replace people on our team?
In our builds it has given people their job back rather than taken it: the receptionist stops juggling the phone and the counter, the paralegal stops retyping names. The repetitive hours go; the people stay, and do the part that needed them.
Can you work with what another agency built?
Usually, yes. We review it first and tell you plainly whether it is worth keeping.
Is Trace available to us?
Yes, as a product with its own site and a 14-day free trial at tracemonaco.com. It is built around Monaco’s obligations; for a similar need elsewhere, talk to us.
How do you measure the hours saved?
Every action the agent takes carries the minutes a person would have spent on it, agreed with you during the prototype. The monthly count adds them up, next to what the agent handed over to a person.
Do you sign NDAs and processing agreements?
Yes, before we see any data. Your template or ours.
Start with a 30-minute call. Keep what it finds.
You tell us where the hours go. We tell you which two or three jobs AI should take first, in a short written note. Free, in English or French.