Translated with AI from the Russian original.

Russian company Smart Engines has introduced the first AI agents for document recognition. Virtual assistants are responsible for creating templates for non-standard documents. Previously, the creation of such templates required project work with the vendor or the participation of specialists on the client's side.

In server solutions, Smart Engines technologies allow processing documents at a speed of 55 documents per second per processor without the use of GPUs. On a mobile phone, it takes less than a second to recognize one page of a document. The AI agents developed by Smart Engines work autonomously and locally - without the use of GPUs or external servers.

The development of AI agents is the result of the company's scientific research in the field of Agentic AI. The new neural network stack is integrated into the Smart Document Engine document recognition system, and AI agents are currently being tested by the company's partners.

AI agents analyze the logic and structure of the document, identify all significant elements: handwritten and printed text fields, barcodes, QR codes, checkboxes, and even complex table structures. It takes an AI agent a few seconds to analyze and add a new form of questionnaire, report, survey or other complex document to the recognition system in the designer.

The user can observe the configuration process in real time, receiving a clear visualization of each stage and accurate algorithm confidence metrics.

Now on the front page

Articles

Why even a PC case should be branded

In Russian conditions, the popularity of PCs assembled by small local companies or in-house corporate IT departments continues to grow rapidly. Such solutions have historically been more popular in Russia than in other developed markets, but today new nuances have emerged in the segment's evolution, which we discussed with Karim LASKRI, Business Director of FSP Group in the CIS region.

News

Storage you can trust in the background: Basis SDS 2.3 released with scheduled diagnostics and an observer role

A storage system is the only infrastructure layer where an error cannot be “rolled back”: neither a reboot nor a configuration rollback will restore lost data. That is why users expect predictability from software-defined storage rather than just new features—ensuring background processes finish what they started, and administrators can see the cluster status not only “right now,” but also over time.