What happens if the agent gets it wrong?
A mistake stays a draft. Anything touching money, stock or new counterparties needs a person to confirm by default. When the agent is unsure, it does not act; it creates a task for a person. Every action is in the log and can be reversed.
Who approves what the agent does?
You decide. At the start we agree where the line is: for example, the agent creates CRM tasks on its own but only drafts invoices and supplier orders for a manager to approve. Once the team trusts the output, the line can move.
Do we have to change 1C or our CRM?
No. We connect to what you already run: via API, 1C data exchange or file export. If a system has no way to accept data from outside, we will tell you during the estimate.
How is this better than a template-based bot?
A template bot breaks when a supplier changes the email format. An agent understands free text and tables in different layouts, so you do not have to force partners into a template.
Will our emails and contracts end up in someone else’s cloud?
If data cannot leave the company, we deploy the agent and the model on your servers, so emails never leave your perimeter. The architecture is designed for 152-FZ, and we work under NDA.
Where do we start and what does it cost?
With the one process that eats the most hours. A pilot starts at RUB 300,000. We price the exact scope by task and hours after a 1–2 day assessment. Send a couple of typical emails and tell us where they get copied to today.