S
Stitex
Case study

Case study: we run what we sell

We are not at liberty to show client data, so we show our own. Everything we sell runs in our production every day — on the same hardware and by the same principles we propose to a customer. The numbers below were taken from live systems on 26 August 2026.

August 26, 20266 min readStitex Technologies
Why a case study about ourselves
Most clients have a publication ban in the contract, and invented case studies with a “major bank” logo fall apart after one phone call. Our own production is the one thing we can show in detail and back up in a live conversation: the numbers below are reproducible and the systems can be demonstrated.

A self-hosted model on our own GPU

Our main tool is a 27-billion-parameter language model running on our own GPU with 32 GB of memory. It serves internal services around the clock: document parsing, call summarisation, content generation, development assistance. The context window is 128,000 tokens — the model holds a hundred-page document in memory at once.

The practical takeaway we pass on to clients: a single consumer-class GPU is enough to cover the work of a small company. The “you need a cluster” conversation starts when the user count runs into the hundreds.

Telephony: 2,254 calls through local transcription

Between March and August 2026 our system handled 2,254 calls. Each one is transcribed by a local speech-recognition model with speaker diarisation, after which a local language model produces a summary: what was discussed, what was promised, whether a response is needed. Recordings and transcripts are personal data, so they are encrypted at rest and kept under a retention policy.

What this demonstrates
Call transcription and analysis are entirely feasible without a single call to an external API. That is exactly the setup we propose to companies whose call recordings cannot leave the building.

Antifraud: 60% of traffic turned out to be bots

Our protection runs on five sites, including our own. Events processed and verdicts issued:

MetricValue
Events processed108,789
Classified as bots65,853
Share of bot traffic60%
Sites protected5

Six events out of ten are automation rather than people. We do not present this as an industry average: these are our sites and our traffic, and your share will differ. But the order of magnitude explains why ad budgets drain unnoticed — see what click fraud is.

Monitoring: 58 nodes, one alert channel

A watchdog of our own looks after the infrastructure: 58 nodes — services, disks, GPU memory, queues, certificates, backup freshness. The checks go beyond “the process is alive”: a synthetic request goes to the language model periodically, because a process can be running and still have stopped answering.

  • Backups are verified by restoring them, not by the existence of a file,
  • Alerts go to a single channel — otherwise people stop reading them,
  • Every incident ends with a root-cause review rather than a service restart.

What this means for you

We do not sell what we have not tested on ourselves. If we propose putting a model inside your perimeter, it is because we live without external APIs. If we say bots consume a noticeable share of traffic, it is because we see it on our own counters. Any number on this page can be walked through in a live demonstration.

How a server for this is built and what it costs is on the on-premise AI server page, and how to calculate the payback is in how to adopt AI in your business.

Let us do the same for you

We will look at your case and say what makes sense for you and what does not. Free, with no strings attached.