Latest publications
AWS SageMaker adds full monitoring for LLM models in production
AWS expanded SageMaker AI with tools for full monitoring of LLM models. New Grafana dashboards track GPU utilization, processing speed, and response quality in real time.
AWS Launches AgentCore to Manage Dozens of AI Agents in Sales
AWS launched AgentCore — a platform to manage 20+ specialized AI agents. Instead of salespeople manually choosing between agents, the system automatically routes requests.
AWS Created NarrateAI — a Business Analytics Assistant on Amazon Bedrock AgentCore
AWS demonstrated how specialized AI agents and a two-layer architecture help scale business intelligence for SMGS divisions using Amazon Bedrock AgentCore.
From Data Overload to Insights: How Verizon Connect Scales AI
Verizon Connect deployed an AI agent that daily processes data from 100,000 users and transforms logistics chaos into understandable insights and recommendations.
AWS Bedrock AgentCore Helped Reduce AI Agent Costs by 97%
AWS Bedrock AgentCore enabled Works Human Intelligence to create AI agents for business support that reduced costs by 97% and improved operational efficiency.
Bedrock Data Automation Learns to Extract Data from Tax Forms and Statements
Amazon Bedrock Data Automation accurately extracts data from bank statements, tax forms, and contracts — the new AWS service automates hours of manual work for fintech and accounting departments.
Snowflake and Amazon Quick Cut AML Verification from One Hour to Five Minutes
Amazon Quick Flows and Snowflake Cortex AI enabled financial companies to verify suspicious transactions in 5 minutes instead of an hour and a half. This significantly eases the work of compliance teams.
Claude Opus 4.8 Arrives on AWS Amazon Bedrock for Agentic Systems
Anthropic and AWS launched Claude Opus 4.8 on the Amazon Bedrock platform with full support for production workloads and agentic systems for AI applications.
AWS outlines five patterns for evaluating deep AI agents
AWS and LangSmith published a practical guide for evaluating complex AI agents. It details five evaluation patterns and methods for configuring offline testing and online monitoring in production, using a text-to-SQL age
How to Connect SageMaker MLflow to Legacy Systems via REST API — AWS Solution
AWS published a solution for integrating SageMaker MLflow into existing ML systems without code rewriting — a Flask proxy with HTTPS and AWS IAM authentication.
AWS SageMaker: Embedding MLflow UI in a Custom Portal via React
AWS published a guide on embedding SageMaker MLflow Apps into a custom portal via React+Flask+SigV4 with deployment through AWS CDK and comprehensive security documentation.
Azerbaijani LLM on SageMaker: How Azercell Solved the Rare Language Problem
Azerbaijani telecom operator Azercell developed its own language model on Amazon SageMaker in six weeks, overcoming data scarcity and morphological complexity.
Amazon Bedrock Helps Strands Create Agents for Dashboard Automation
AWS unveiled a solution based on Bedrock AgentCore and Strands for dashboard automation using AI agents that understand natural language and transform data into business insights.
OPLOG developed three BI-agents on Amazon Bedrock with Claude Sonnet
OPLOG developed three AI agents for automating business analytics tasks using Strands Agents SDK and Amazon Bedrock AgentCore.
Amazon Bedrock AgentCore Will Allow Processing Documents Without Limitations
Amazon has introduced a way to bypass context limitations in language models through AgentCore Code Interpreter, enabling analysis of documents of any size using recursive processing.
AWS AgentCore: A Framework for Multi-Tenant AI Agents in SaaS
AWS unveiled the AgentCore framework for multi-tenant AI agents. The system addresses architectural challenges of data isolation, scaling, and managing multiple clients in SaaS applications.
AWS Deployed AI Agents to Optimize Radiologists' Workflows
Artificial intelligence is teaching hospitals to better distribute diagnostic studies among radiologists, solving the problem of diagnostic delays and physician burnout.
Amazon Nova Act Receives HIPAA Certification for Healthcare Applications
Amazon has added HIPAA compliance for Nova Act models, opening the path for using AI in healthcare applications with secure patient data processing.
Amazon Bedrock: Custom Lambda-evaluators for AI Agent Control
AWS showed how to integrate Lambda functions into Bedrock AgentCore for automatic validation of agent responses—from fact-checking to PII detection.
Amazon Bedrock Adds Three Ways to Manage AI Agent Tools
AWS Bedrock offers developers a choice between a Docker sandbox, managed Code Interpreter, and an Anthropic SDK-compatible proxy for calling tools from AI agents.
AWS accelerated ML pipelines in SageMaker Feature Store with three new capabilities
The AWS SageMaker Python SDK gained three new capabilities for managing ML data: integration with Lake Formation, support for Iceberg, and pipeline optimization.
AWS Bedrock AgentCore Memory: how to give AI agents long-term memory in Kiro CLI
AWS integrated long-term memory into Kiro CLI through Bedrock AgentCore Memory and a custom MCP server. AI agents in the terminal can now remember the context of previous interactions.
Amazon Nova Sonic: Three Architectures for Voice Agents
AWS showed how to build voice agents with Amazon Nova Sonic and Bedrock AgentCore. The article breaks down three architectural schemes and latency minimization tactics for interactive dialogues.
AWS SageMaker and vLLM: real-time streaming speech transcription
AWS SageMaker with vLLM enables real-time speech processing through a streaming architecture. Instead of waiting for a full recording, the system processes audio in chunks and delivers results instantly.
Multimodal judges: how AWS evaluates the quality of image descriptions
AWS has introduced a new way to evaluate AI models that describe images. Multimodal evaluators check whether a model actually relies on the content of the image.
Amazon SageMaker AI Gets Full OpenAI-Compatible API Support for Developers
Amazon SageMaker AI now supports an OpenAI-compatible API for real-time endpoints. Developers can use familiar tools by simply changing the endpoint URL.
Amazon Nova 2 for content moderation: a structured prompting approach
Amazon presented a prompting methodology for content moderation with Nova 2 Lite. Tests on three open datasets showed better results than other models.
Aderant accelerated Amazon Quick cloud operations 10x
Aderant unified search across six systems in the Amazon Quick cloud and sped up document search by 90%.
AWS Introduces Payments for AI Agents — Bedrock AgentCore Integration with Coinbase and Stripe
Amazon Web Services has introduced Amazon Bedrock AgentCore Payments — a new set of features that enables AI agents to autonomously make payments for the services they use.
Verifiable rewards: how AWS improves neural network training
AWS introduced the RLVR approach — training with verifiable rewards — which improves model accuracy on math tasks and code generation.