Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

COMPANY · ENTITY #5988

Amazon Cognito

Related event timeline, sources and context from the news index.

EVENT TIMELINE

14

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon Bedrock Managed Knowledge Base gains AgentCore memory integration via AgenticRetrieveStream

Amazon describes an opt-in integration that lets Bedrock Managed Knowledge Base use AgentCore memory as a retrieval source by adding a memoryConfiguration to AgenticRetrieveStream. The feature stores conversations, extracts durable facts, retrieves relevant per-user memory alongside document search (respecting ACLs), and saves turns back to memory; the post includes a multi-tenant sample using Cognito, S3 ACLs, and IAM controls.

6.0

CODING · 1 SOURCE · AWS Machine Learning

AWS publishes cross-account A2A multi-agent reference architecture using LangChain and Strands

AWS provides a deployed reference architecture showing how the Agent-to-Agent (A2A) protocol can connect LangChain-based enterprise orchestrators with Strands Agents–based SaaS agents across separate AWS accounts using OAuth/OIDC, Amazon Cognito, Bedrock AgentCore, API Gateway, ECS/Fargate and Agent Cards. The post includes implementation patterns, three Jupyter notebooks to deploy the system, and an end-to-end test; A2A is now a Linux Foundation project and AWS is listed among its supporters.

7.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Amazon describes fine-grained access control for Bedrock Managed Knowledge Base tools using AgentCore Gateway

Amazon published a design and sample implementation showing how to prevent LLM-driven agents from accessing data a user isn’t authorized to see by injecting verified user attributes at the AgentCore Gateway and scoping searches with Bedrock Managed Knowledge Base ACL awareness. The pattern uses JWTs (via Amazon Cognito), a gateway request interceptor (AWS Lambda), Policy in AgentCore with Cedar evaluation, and resource-based role restrictions to enforce userContext when exposing the knowledge base as MCP tools.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Automating AWS Agent Registry updates for MCP servers with push-based architecture

A post outlines an event-driven architecture that detects UpdateAgentRuntime events from Amazon Bedrock AgentCore and automatically synchronizes MCP server tool/schema changes to the AWS Agent Registry using CloudTrail, EventBridge, and Lambda. The sample supports single- and multi-account setups, authenticates via AgentCore Identity (OAuth), and only updates existing pre-registered registry records (it does not create new records).

5.0

COMPANIES · 1 SOURCE · AWS Machine Learning

TCS builds agentic test orchestrator using Amazon Bedrock AgentCore

Tata Consultancy Services (TCS) developed a multi-tenant Agentic Test Orchestrator that turns requirements into executable, governed API and browser tests by running specialized agents on Amazon Bedrock AgentCore runtime. The SaaS platform, built with the Strands Agents SDK and AWS services (EKS, ECS, S3, DynamoDB, CloudWatch), enforces per-tenant isolation and automates generation, execution, and reporting of tests for BFSI clients.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Serverless MCP server on Amazon ECS Fargate provides centralized LLM access to enterprise data lake

Amazon’s NASC team built a serverless Model Context Protocol (MCP) server deployed on Amazon ECS with AWS Fargate to act as a centralized, agent-agnostic gateway between LLM agents and an enterprise data lake. The metadata-driven FastMCP implementation integrates with Amazon Bedrock (with Guardrails), Athena, Redshift, S3, and Cognito, enforces permissions at the MCP layer, and lets teams add datasets via JSON metadata without per-agent code changes.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Eon uses Amazon Bedrock AgentCore Gateway to centralize multi-cloud MCP access

Eon implemented a centralized authenticated gateway using Amazon Bedrock AgentCore (Gateway, Runtime, Policy, Identity) to replace per-tool credentials and local MCP processes, giving engineers and autonomous agents unified access to investigation tooling across AWS, GCP, and Azure. The change reduced developer onboarding for investigation tooling from about two days to roughly two minutes and lets Eon's autonomous SRE agent (Claude on Bedrock) access the same tools with separate identities and permissions.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

AWS Agent Registry enables runtime discovery of MCP servers and agent skills

AWS describes AWS Agent Registry, a managed catalog for registering and semantically searching Model Context Protocol (MCP) servers, agents, and agent skills so orchestrators can discover and instantiate tools at runtime rather than hardcoding endpoints. The post includes a Python reference that wires Amazon Bedrock AgentCore Gateway, AgentCore runtime A2A agents, and an orchestrator that searches the registry, constructs clients from descriptors, and invokes capabilities (authentication must be obtained separately).

6.0

CODING · 1 SOURCE · AWS Machine Learning

Build agentic intelligent document processing on Amazon Bedrock AgentCore with Strands Agents

AWS published a how-to for an agentic intelligent document processing (IDP) solution that uses Amazon Bedrock AgentCore and the open-source Strands Agents SDK to classify, extract, validate, and self-learn from business documents. The architecture ties AgentCore runtime and identity capabilities to AWS services (Textract, S3 Vectors, Aurora DSQL, Lambda, EventBridge, DynamoDB, ECS) in multi-agent workflows so new document formats can be processed and reused with minimal manual template configuration.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

AWS publishes tutorial to build a voice travel concierge with Bedrock AgentCore and Nova 2.5 Sonic

AWS published a how-to demonstrating a voice travel concierge built with Amazon Bedrock AgentCore (runtime and Gateway), Amazon Nova 2.5 Sonic for real‑time speech, and Amazon Bedrock Knowledge Bases, using the AWS CDK and the Model Context Protocol (MCP) to connect the agent to backend services. The post details architecture, components (authentication, data stores, Lambdas, API Gateway), and a sample airline implementation that keeps the agent loosely coupled to existing systems.

5.0

COMPANIES · 1 SOURCE · AWS Machine Learning

AWS publishes 'Adjudicated Query' pattern for provable lease compliance using Amazon Quick

AWS demonstrates an "Adjudicated Query" design pattern and reference architecture that combines a generative-AI chat surface (Amazon Quick) with a deterministic, versioned rules engine to run auditable, provably complete compliance sweeps (example: tens of thousands of leases). The architecture separates conversational translation/narration (model) from pass/fail determinations (rules engine), emits a completeness receipt, and shows an end-to-end deployable sample using MCP, Amazon Bedrock, Cognito, API Gateway, Lambda, and Aurora Serverless v2.

6.0

CODING · 1 SOURCE · AWS Machine Learning

Amazon Bedrock AgentCore Gateway adds secure Web Search access to Claude Desktop

AWS shows a step-by-step walkthrough to connect Claude Desktop on Amazon Bedrock to AgentCore Gateway’s managed Web Search, using JWT-based inbound authentication with Amazon Cognito and AWS IAM Identity Center so query traffic stays within AWS. The guide covers configuration, SAML/OAuth federation, and notes regional availability in us-east-1, eu-west-1, and ap-northeast-1.

6.0

COMPANIES · 1 SOURCE · AWS Machine Learning

Reactiv automates mobile app updates with Amazon Bedrock AgentCore, cutting configuration time 80%

Reactiv says it built a three-agent AI Scheduler using Amazon Bedrock AgentCore and the Strands Agents SDK to autonomously update Shopify merchants' native apps; the company reports an 80% reduction in merchant configuration time and 33% faster path to production. The implementation uses AgentCore runtime, memory, and identity for managed agent execution, persistent per-merchant memory, and native hosting of their Config MCP.

5.0

COMPANIES · 1 SOURCE · AWS Machine Learning

EXL launches AI-powered Medical IDP solution on AWS

EXL has combined its Xtrakto.AI intelligent document processing application with a domain-tuned EXL Insurance LLM and deployed the pipeline on AWS (using Amazon SageMaker AI and Amazon Bedrock among other services) to extract, summarize, and query medical records at enterprise scale, aiming to cut claims and underwriting review time. The end-to-end solution runs within an AWS Region and uses AWS services for ingestion, orchestration, OCR, model training/inference, and secure access control.

5.0