What we do
We choose an open model by your 50 requests: 8–9 billion, 30 billion or 70 billion parameters, Russian-language or global. We size the hardware with calculators and give a specification to buy or rent. We set up the engine for the load: one user or parallel work for a department. We build the agents behind one model interface, so the cloud and a local model switch by a setting. We set up routing for a hybrid design and anonymization before anything goes to the cloud. We add monitoring and hand everything to your engineer with instructions.
Pilot: 14 days, from $1,499
One agent on one process, on your own or rented hardware. The metric is in the contract: share of requests without an operator, minutes per document, response time. An exam on 50 requests before and after. The result: a working agent, a report with numbers and a hardware estimate for scaling. If the local model cannot handle the task, we say so in the report and show where the cloud can.
AI agent team: 4–6 weeks, from $4,999
3–5 agents on one local model with a shared knowledge base and task queue: for example, sorting incoming requests, answers from documents, draft preparation and a manager dashboard. A server or workstation to our specification, an engine for parallel work, and routing to the cloud for tasks on anonymized data. For large companies: from $18,000 in 2–3 months, with several departments and integrations.
Support: from $480 a month
Model and engine updates with a repeat exam, monitoring, incident reviews and a plan for a card failure. An AI director from $999 a month: a person who runs your agents and local infrastructure as a product, with a report to the top manager.
What we do not do
We do not sell hardware or take commissions from sellers: you buy to the specification wherever you like. We do not promise that a local model will do the job of a flagship model: the pilot tests this. We do not train models from scratch; fine-tuning on your data is possible as a separate project. We do not give legal opinions on 152-FZ and 243-FZ: we describe the architecture, and your lawyer gives the opinion.
Why we count both sides
We build agents on both cloud and local models, so we have no need to sell you a server. The calculators in this section show when the cloud is cheaper, and we say so in the pilot. Founder Mike Mozg runs a media channel and reviews cases in public; the numbers on this page are the same as in the contract.