| Result | requests handled 20 times faster on a local LLM, 1.5 times more requests with no new hires |
| Source | Digital Platforms catalog, case no. 3475, 2 September 2026 |
| A similar task for us | AI employee |
| Industry | IT companies |
What was done and what came out
- The model extracts and structures data from requests instead of manual reading, and support answers come from the knowledge baseAI knowledge base. An AI knowledge base is a set of selected and prepared company documents that an AI assistant searches for answers: rules, instructions, a product catalog and answers to common questions..
- For testing agent scenarios, the team set up an MCP serverMCP server. An MCP server is a program that gives an AI application access to one system through the Model Context Protocol (MCP): it tells the AI which actions and data are available and carries out the model’s requests..
- Request processing grew 20 times faster.
- Requests grow 11% a month on average, and quality holds.
- Year-on-year growth of 1.5 times was handled without hiring, so the company avoided a 7-fold increase in staff.
What to take for yourself
One local modellocal LLM. A local LLM is a neural network that runs on your own computer or server, not in a vendor’s cloud, so your data goes nowhere. covered three areas at once: requests, support and development. The hardware pays off when several tasks load it.
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.
- Digital Platforms catalog, case no. 3475 (platforms.su)· 2 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
- Digital Sector and an IT infrastructure client: AI contract analysis agent in the client’s closed environment; in the integrator’s own testing, agents freed 20% of team time
- VK Tech: two models fit into 22.4 GB of 24 GB of video memory with a 65,536-token context
- LANIT: requirements gathering 4 times faster, document search time 66% lower on a local LLM platform
- Pulkovo Airport: AI secure code review plugin in a closed network: over 90% accuracy on checking findings and up to 85% on fixes
- Step agroholding: its own AI ecosystem on local neural networks, so data never goes to public services
- 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.