Skip to content

Research & explainers

Practical Guides · Latest

Reusable workflows and tutorials

6 selected reportsIn the last 30 days 6 reportsIndexed 31 reports

RSS
updated

Selected: Practical Guides

Oct 27TueItems 1–6
  1. AWS Machine Learning BlogFirst-party

    AWS launches Managed Amazon Bedrock Knowledge Base with AgenticRetrieveStream API for multi-turn retrieval

    AWS introduces a Managed Amazon Bedrock Knowledge Base that transforms retrieval into an agentic capability, replacing single embed-and-fetch calls with multi-turn planning and tool-driven retrieval. The AgenticRetrieveStream API enables a reasoning agent to decide whether to retrieve, which knowledge base to consult, and whether to iterate before composing a grounded, cited answer. This addresses limitations of ordinary RAG, such as answers spanning multiple corpora or requiring follow-up lookups after initial results. The service is now available as a first-class feature, eliminating the need to manually manage OpenSearch Serverless collections. AWS CDK users can now provision the knowledge base and AgenticRetrieveStream as stacks, though observability remains critical due to the non-deterministic paths agents take during retrieval.

    Read source aws.amazon.com
Oct 23Fri
  1. AWS Machine Learning BlogFirst-party

    AWS SageMaker AI Uses Two Measurements to Set TTS Auto‑Scaling Targets

    AWS deployed the 82‑million‑parameter Kokoro‑82M text‑to‑speech model on a SageMaker AI real‑time endpoint and replaced guesswork with two live‑endpoint measurements. The maximum concurrency a single instance can handle before breaching the service‑level objective (Q_max) was measured at 50 requests, and the end‑to‑end time for a scale‑out (T_total) was 320.2 seconds. These values were used to calculate precise scale‑out and scale‑in thresholds and cooldown periods, eliminating the hidden risk of over‑ or under‑provisioning that traditional auto‑scaling metrics miss.

    Read source aws.amazon.com
Oct 21Wed
  1. AWS Machine Learning BlogFirst-party

    AtScale Builds a Dimensional Semantic Layer for Agentic AI on AWS

    AtScale introduces a dimensional semantic model on AWS, replacing graph‑based layers used in earlier posts. The model, defined in the open Semantic Modeling Language (SML) and versioned in Git, is exposed via SQL, XMLA, and the Model Context Protocol (MCP). A Strands agent on Amazon Bedrock AgentCore queries this layer, with identity and role‑based access control propagated through AgentCore’s identity features. The solution is deployed on Amazon EKS using AtScale’s Helm chart.

    Read source aws.amazon.com
  2. AWS Machine Learning BlogFirst-party

    Strategy Mosaic Enables Agentic AI on AWS by Providing a Unified Semantic Layer for Bedrock AgentCore

    Strategy Mosaic is used as a semantic layer on AWS to support agentic AI via Amazon Bedrock AgentCore. The solution models a Customer‑360 domain across Amazon Redshift and Amazon Aurora with two linked models, avoiding ETL. Mosaic’s dimensional model exposes a Model Context Protocol that lets a Strands agent reach the semantic layer, while row‑level and object‑level security propagate end‑to‑end. The same governed definitions can be shared with Power BI, Tableau, notebooks, and custom apps through JDBC/ODBC, XMLA, and REST.

    Read source aws.amazon.com
  3. AWS Machine Learning BlogFirst-party

    AWS Integrates Denodo Semantic Layer with Bedrock AgentCore for Federated Customer 360 Queries

    AWS demonstrates how to build a semantic layer using Denodo that federates Amazon Aurora, Amazon Redshift, and an on‑premises PostgreSQL database into a single Customer 360 view. The Denodo MCP Server exposes governed views to a Bedrock AgentCore‑hosted agent via the Model Context Protocol, while AgentCore handles authentication and credential management. The setup supports row‑ and column‑level security and can run on Denodo Agora or self‑managed EC2/EKS instances.

    Read source aws.amazon.com
Oct 8Thu
  1. Hugging Face BlogFirst-party

    User Trains Seven Mini Models with ML-intern for Just $103

    A user leveraged Hugging Face's ML-intern to train and release seven mini models at a total compute cost of around $103, covering various functionalities like disease identification, character drawing, camera angle LoRA, and lightweight student models.

    Read source huggingface.co