Yandex Launches NeuroExpert AI Service for Personalized Knowledge Search

Posted by By Dan Taylor 3 Min Read

Yandex has launched a new AI-powered tool called NeuroExpert. The service helps users extract answers and insights from their own uploaded data. It supports various file types including links, documents, PDFs, audio, and video.

NeuroExpert builds a personal knowledge base from these files. It can then summarize content, compare documents, generate new text in a specific style, or answer user questions using the uploaded information.

User-Focused AI With Document Support

Currently in beta, NeuroExpert allows up to 25 uploads per user. It is available to all users, including Yandex 360 clients. After the beta phase, users will be able to upload more files and links.

The service is designed to be useful in both work and everyday scenarios. For example, users can upload product reviews and video links to receive a side-by-side comparison. It can also interpret board game rules to resolve in-game disputes.

Built With Yandex’s AI Stack

NeuroExpert uses a set of Yandex technologies to understand different types of data:

  • VLM (Visual Language Model) helps analyze images, graphs, and diagrams.
  • ASR (Automatic Speech Recognition) is used to process audio and video.
  • OCR (Optical Character Recognition) extracts text from images.

Final answers are generated by YandexGPT 5 Pro, Yandex’s latest large language model. The model uses retrieval-augmented generation (RAG) to respond based only on the user’s uploaded content, not on pre-trained memory. This helps reduce inaccuracies or hallucinations.

What Is Retrieval Augmented Generation?

RAG is a method that allows a language model to use external data without retraining. It pulls relevant information from uploaded files and combines it with the model’s understanding of language to deliver high-quality answers.

This approach makes updating the model’s knowledge easier and improves accuracy in real-world use. A similar system is already used in Yandex’s “Search with Neuro.”

Business Use Coming Soon

Yandex plans to expand NeuroExpert to include more features for businesses. The tool could search internal documentation, speed up onboarding, and support daily tasks.

Yandex uses NeuroExpert to manage corporate documents, research, and instructions. Businesses can apply for early access through the official website.

This launch follows Yandex’s recent decision to discontinue Turbo page support in Search.

Source: Yandex press release

Dan Taylor
View More Posts
Dan Taylor is the founder and editor of International Search Insights (ISI), the publication behind ReadIsi, and a Partner and Head of Innovation (Search & AI) at SALT.agency. He has worked in search for more than a decade, in-house and agency-side, and is regarded as one of the West’s leading voices on search engines beyond Google, including Yandex, Baidu, Naver and Cốc Cốc. On ReadIsi, Dan covers the engines and AI answer platforms that English-language coverage tends to miss: Baidu and ERNIE, Yandex and Alice AI, Naver, Cốc Cốc, Shenma, Sogou, WeChat and Weibo search, plus DeepSeek and Alibaba’s Qwen. He also keeps dated records of documented changes, such as the Yandex, Baidu and Naver algorithm update histories and the DeepSeek, ERNIE and Qwen model update histories. His approach is to take learnings from global search engines and apply logic with a high evidence threshold. A claim needs a source, patterns seen in one market are treated as a hypothesis until they are checked in another, and where the evidence is thin he says so. For brands, that means advice built on what can be shown, with measurement that separates being cited from being chosen. Dan is credited with coining the term “edge SEO” and won the inaugural TechSEO Boost research competition in 2018 for his work on CDN and edge changes for SEO. In 2026 he was credited with coining “Infinite Tail” to describe how keyword research is changing with AI search. He is the author of AI Search Marketing For The Travel Sector, writes for Search Engine Journal, Search Engine Land and Travel Marketing Guy, and has advised technology, SaaS, travel and enterprise ecommerce brands, including Cloudflare, GitLab and Airbnb. He has given multiple talks and panels at the International Search Summit in Barcelona, and has also spoken at Optimization Moscow, brightonSEO, Google Search Central Live Deep Dive Asia in Bangkok, Athens SEO and the Asia SEO Virtual Summit 2026, where his talk looked at how Baidu, Naver, DeepSeek, Tencent, Cốc Cốc and Yandex built their own AI answers.
Founder & Editor