AI/ML
Sber — Guardian of Truth
Checks GigaChat answers for factual hallucinations and returns a probability of invented facts — no external APIs or fine-tuning.
- Scope of work
- Design · Development · ML · NLP · Testing
- Year
- 2025
- Discipline
- AI/ML
A dashboard for measuring GigaChat hallucinations: comparing models by answer accuracy and the share of invented facts.
Gallery
Similar task?
Tell us about the project and we will propose an approach, a timeline and a staged estimate.
Services used on this project
- AI and ML developmentWe build AI that solves a defined task and pays for itself, not demos for the sake of demos. Classifiers, recommendations, text and document processing, LLM assistants, and model integration into an existing product.
- IT consulting and product auditThe most expensive mistakes in software happen before the first line of code: a misread problem, a stack chosen out of a contractor’s habit, and a specification that does not exist. Consulting exists to settle all of that before the development meter starts running: what to build, out of what, at what cost and in which order. The result is a document, not an opinion on a call.
- CRM implementation and sales automationEnquiries from messengers, email and calls get lost when the only place tracking them is a sales manager’s memory. A CRM fixes this, but only when it is configured around your actual sales process rather than left as the out-of-the-box default. We implement amoCRM and Bitrix24, set up automation, and connect everything to the website, telephony and analytics.
