Strands Agents

Headlines · 5

1. 5d
   Build self-improving document processing with Amazon Bedrock AgentCore

   AWS published a technical guide for building an agentic intelligent document processing (IDP) system on Amazon Bedrock AgentCore, in which eight specialized agents collaborate across two graph workflows built with the open-source Strands Agents SDK. A new document type goes through a training workflow — an Analyzer extracts text with Amazon Textract, a Matcher searches Amazon S3 Vectors, an Instructions agent generates extraction prompts, an Extractor produces structured JSON and a Validator checks it against schemas and business rules in Amazon Aurora DSQL — while documents matching a known layout skip prompt generation in an automation workflow. In the sample purchase-order scenario, the first run took 3 minutes 49 seconds and a repeat document took 1 minute 30 seconds, and AWS estimates about $58 per month for 10 training plus 1,000 processed documents in US East (N. Virginia), with model inference roughly 85 percent of that cost. AWS cites IDC figures that document-related challenges cost organizations $19,732 per information worker annually and cut productivity by 21.3 percent.

   AWS Machine Learning Blog · 🔥 0
2. 5d
   AWS tutorial: build a slide-generating agent on Amazon Bedrock AgentCore

   An AWS Machine Learning Blog post walks through building a system that turns quarterly reports, compliance documents and market analyses into PowerPoint decks using Amazon Bedrock AgentCore. A single supervisor agent runs on AgentCore runtime and uses the Strands Agents framework to route requests between a document-generation tool and a summarization tool, with a RAG pipeline built on Amazon Bedrock Knowledge Bases, Amazon OpenSearch Serverless and Amazon Titan Text Embeddings v2. Anthropic Claude Sonnet 4.6 writes the content, Stability AI Stable Image Inpaint creates slide images, and a .NET 8 minimal API exposes the workflow to existing enterprise applications; AWS says the flow finished in under 90 seconds in its internal testing, and a public code repository is included.

   AWS Machine Learning Blog · 🔥 0
3. Oct 7
   Cornerstone cuts database diagnosis time 78% with Bedrock-based Orion AI

   Cornerstone OnDemand's Enterprise DataOps team built Orion AI, a multi-agent system on Amazon Bedrock and AWS's open-source Strands Agents framework, using a hub-and-spoke topology in which a meta-orchestrator routes work to 13 domain-specific agents, including three SQL Server diagnostics agents. According to the AWS blog post, database diagnosis time fell from about 45 minutes to 10 minutes per incident (a 78% reduction), manual lifecycle steps dropped roughly 70%, SRE-to-data-team reporting lag went from 15 minutes to real time, and redundant alerts fell by a median of 65%. A three-person team delivered the system in six months on Amazon ECS, with Amazon Bedrock AgentCore providing cross-session memory.

   AWS Machine Learning Blog · 🔥 0
4. Oct 6
   AWS tutorial: building a voice travel concierge with AgentCore and Nova Sonic

   An AWS Machine Learning Blog tutorial walks through deploying a voice travel concierge on Amazon Bedrock AgentCore: Amazon Nova 2.5 Sonic handles real-time speech-to-speech, Strands Agents defines the agent, and AgentCore Gateway exposes airline backend endpoints as MCP tools, with Amazon Bedrock Knowledge Bases answering policy questions via RAG. The post says Nova 2.5 Sonic improves tool calling and multi-step agentic task completion and supports bidirectional streaming, asynchronous tool calls, latency masking and barge-in. The solution deploys with AWS CDK and a React front end on Amplify.

   AWS Machine Learning Blog · 🔥 0
5. Oct 5
   AWS shows layered evaluation for multi-agent systems with AgentCore Evaluations

   An AWS blog post explains how to assess multi-agent systems with Amazon Bedrock AgentCore Evaluations, combining built-in evaluators (helpfulness, task success, instruction following, tool selection) with custom evaluators for domain rules such as constraint satisfaction, route feasibility and SQL correctness. The walkthrough uses a fictional retailer, AnyCompany Retail, building a supply-chain decisioning system with the Strands Agents SDK: one orchestrator agent plus optimization, distribution, routing and analytics sub-agents running on AgentCore runtime with memory and observability. A separate explainability layer of six cross-cutting evaluators checks decision rationale, evidence attribution, constraint reasoning, trade-off explanation, tool-use explainability and assumption disclosure; AgentCore Evaluations runs in on-demand mode for benchmarks and CI/CD gates, and online mode to sample production traces into CloudWatch dashboards and alarms.

   AWS Machine Learning Blog · 🔥 0

Experience and discussion from the community

Share my Strands Agents experienceAsk about Strands Agents