Astra Group Releases Low-Code Astra AI Platform for Building Corporate AI Agents in Closed Environments
Astra Group has introduced the Astra AI Platform, a low-code constructor for corporate AI applications that can be deployed locally in closed environments without dependence on foreign cloud services.
The solution is aimed at small and medium businesses as well as large corporations and is positioned within the company’s existing ecosystem for secure development processes, including ASOC and DevSecOps practices.
According to the developer, the platform reduces implementation time from several months to just a few days. It consists of two integrated constructors: an ML module responsible for training and deploying machine learning models, and an LLM module focused on language assistants, document-based search, and workflow automation.
Applications are built from visual blocks that can be configured and debugged in real time. When visual tools are insufficient, developers may edit the underlying code or add custom blocks written in Python.
The platform supports enterprise knowledge bases for RAG retrieval, allowing agents to search internal company documents. External tool connections enable integration with CRM, ERP, email systems, and web search services.
Multiple agents can be combined and assigned different tasks. Example scenarios include analytics, financial operations, technical support, and risk monitoring.
In one company-provided demonstration, the models processed ten pages of engineering drawings and specifications within five minutes, preparing structured data for downstream engineering systems.
The product is registered in the Russian domestic software registry and is now available to customers.
Related articles
Yandex Black October: How Architectural Flaws and Capacity Mismanagement Turned Data Center Losses Into a 11-Day Fintech Coma
In October 2026 three Yandex data centers in Central Russia were physically destroyed within days, triggering the collapse of Yandex Cloud and multiple core services. Between the first and third site failures engineers had 74 hours to restore quorum and rebalance workloads yet failed to do so because Control Plane components remained tied to the lost zone and spare capacity had been eliminated to cut costs. Core banking and BNPL systems entered Read-Only mode after losing quorum, forcing a complete stop-the-world reconciliation that lasted until 22 October. Backups stored inside the same regional S3 buckets proved unusable, resulting in a seven-day RPO and primary-key collisions after restoration. The incident exposed that Metro-Cluster designs had been incorrectly treated as full Disaster Recovery and that aggressive AP microservice patterns created logical split-brain conditions outside the database layer.
Multi-Tenancy Isolation in VictoriaMetrics, VictoriaLogs and Grafana: Building Client Separation in a Shared Stack
Voltir runs a single shared monitoring stack consisting of VictoriaMetrics, VictoriaLogs, Grafana and vmalert for all customers instead of deploying separate instances per tenant. Isolation relies on numeric account IDs enforced at every layer: nginx validates tokens against the platform API before proxying writes, Grafana data sources hard-code tenant accounts, and vmalert rules receive automatic account filters. The team discovered that a single malformed rule or template could break alerting for every tenant because vmalert loads the entire rules directory at once. They also found that Grafana automatically created personal organizations granting Org Admin rights, accumulating hundreds of orphaned organizations and users that consumed disk space and resources. A dedicated cleanup module plus hourly reconciliation now removes rules, organizations, series and users when a tenant is deleted, while isolation tests verify both data and API objects across tenants.
The Real Costs of Using Claude and GPT for Russian Businesses Exposed
Accessing generative AI models like Claude and GPT has become straightforward for Russian companies, yet calculating their true expenses remains complex. Hidden factors such as intermediary commissions, currency conversion rates, taxes, and the often-overlooked costs of model reasoning tokens can double or triple initial estimates. Founder Vitaly Nagay of the Heli service analyzed these financial and organizational risks for Russian firms relying on foreign AI providers. In one example, a support department processing 20,000 monthly queries sees costs rise from $240 to $480 when reasoning tokens are included. Nagay recommends evaluating providers by dividing actual ruble charges by the model's official dollar pricing to reveal hidden markups. Additional concerns involve data control, document compliance, and access history when employees use personal subscriptions. Companies are advised to verify billing details, data storage policies, and issue dedicated API keys with spending limits before procurement.
Decoding Windows 10 and 11 Error Codes: How to Identify Root Causes and Fix System Failures
Windows frequently reports problems using codes that seem aimed only at developers, leaving users to decipher issues like 0xc000007b, 0x800f081f, and Kernel-Power 41 on their own. The article explains that error codes typically describe failed operations rather than underlying causes, such as access denials stemming from permissions, security software conflicts, or corrupted components. It provides a structured diagnostic approach starting with version checks via winver, context analysis of when errors occur, and preservation of critical data before troubleshooting. Detailed tables cover common codes across update, application launch, driver, and boot failure categories, while sections address Blue Screens of Death, Windows Update problems, driver errors like Code 43, and event log analysis. Recovery methods including DISM, SFC, safe mode, and point-in-time restore are outlined with warnings against risky generic fixes. The guide emphasizes sequential diagnosis to avoid data loss and notes the end of Windows 10 support.