| Result | requirements gathering 4 times faster, document search time 66% lower on a local LLM platform |
| Source | Digital Platforms (Tsifrovye platformy), case no. 2874 |
| A similar task for us | AI employee |
| Industry | IT companies |
What was done and what came out
- The problem the platform solves: with cloud modelscloud AI model. A cloud AI model is a neural network that runs on the servers of a provider. You use it through a website, an app or an API, and you pay for the volume of requests., including foreign ones, the code base and documents leave the company network.
- According to the group, AI requirements gathering and analysis with an LLMlarge language model. A large language model (LLM) is a neural network trained on a huge amount of text. It writes, summarizes and analyzes text on request. is 4 times faster, and developers complete twice as many tasks.
- Finding a document through the internal chatbotchatbot. A chatbot is a program that exchanges messages with a person in a chat window: on a website, in a messenger or in an app. takes 66% less time, and the chatbot has been in production since summer 2025.
- The platform runs models of 8–14 billion parameters on a standard server and larger ones on dedicated hardware.
- It entered Russia’s registry of domestic software in April 2025.
- No cash effect was disclosed.
What to take for yourself
Integrators sell local AI as a platform: an interface, pipelines, access rights and updates. The model is only one part of such a delivery.
AI agents on a local model for your team: a pilot in 14 days. A pilot AI agent on a local model in 14 days from $1,499 with the metric in the contract, on your hardware or on rented GPUs. An AI department of 3–5 agents in 4–6 weeks from $4,999. You buy the hardware to our specification.
Sources and fact-checking
The facts and numbers on this page come from the publication. Data type: project catalogue entry. The company is not our client: the page shows what a smaller company can repeat from this experience. Checked by the editors on 30 September 2026.
Found a mistake? Tell us
Similar cases
- AI department B2B services case: from one lead agent to a team that protects every lead
- B2B services lead handling: answer every request before the client leaves
- Samsung Electronics: ban on outside generative AI services after a source code leak, own tools in development
- ETH Zurich, EPFL and CSCS, Switzerland: fully open sovereign model Apertus: 8 and 70 billion parameters, 15 trillion tokens, more than 1,000 languages
- Ramp: 30,000 hours of manual work a month
- Developer MR: Project finance AI controller in an isolated environment: 80% less time on credit document analysis
- Moscow City Health Department: AI assistant for hospital analytics on a local language model: data does not leave the network
- All materials in the industry: IT
Prices and measurements in this section were checked against the sources at the bottom of each page. We build AI agents on cloud and local models and do not sell hardware. Calculations are estimates; legal conclusions on data protection come from your lawyer.