CREDIT: JASON DOIY
How can this be achieved?
Yuriy: We achieve this through a fundamental shift in AI architecture. Instead of treating Large Language Models( LLMs) as the“ source of truth” or the core reasoning engine – which is exactly what leads to hallucinations – we use them strictly for what they do best.
We harness their immense power to process messy, unstructured data, extracting explicit knowledge from a massive variety of PDF manuals and maintenance reports, alongside tacit knowledge captured from handwritten notes and direct communication between experts and AI. This is all transformed into a strict, deterministic knowledge base. We process and validate this knowledge heavily in the cloud with human experts in the loop. Only then do we push the highly verified, compiled intelligence down to the edge – right to the factory floor – for real-time execution.
At the edge, we use formal logic for core intelligence and traditional machine
72 May 2026